SlideShare a Scribd company logo
1 of 23
Download to read offline
CVPR 202
0

주성훈, VUNO Inc.


2021. 10. 17.
PR-351
1. Research Background
2. Methods
1. Research Background 3
Class incremental learning
많은 real-world application에서, streaming data로부터 점진적으로 새로운 class들을 학습해야 하는
경우가 있는데, 이를 class incremental learning이라고 한다.
Incremental	learning	aims	to	learn	efficient	machine	models	from	the	data	that	gradually	come	in	a	sequence	of	
training	phases.	Closely	related	topics	are	referred	to	as	continual	learning	and	lifelong	learning.
Xiao, Tianjun, et al. "Error-driven incremental learning in deep convolutional neural network for large-scale
image classification." Proceedings of the 22nd ACM international conference on Multimedia. 2014.
/ 23
2. Methods
1. Research Background 4
• 새로운 incremental phase에서 학습된 모델은 old class를 쉽게 잊는다
Motivation - catastrophic forgetting issue
/ 23
2. Methods
1. Research Background 5
(Recap from PR-339) Previous works - Replay based method
Old data에 대한 additional memory를 만들고, 이를 활용해 catastrophic forgetting을 막는다.
IL2M (ICCV 2019)
Figure from: Belouadah, Eden, and Adrian Popescu. "Il2m: Class incremental learning with dual memory." ICCV 2019.
/ 23
2. Methods
1. Research Background 6
(Recap from PR-339) Previous works - Replay based method
Old data에 대한 additional memory를 만들고, 이를 활용해 catastrophic forgetting을 막는다.
[iCaRL] Rebuffi, Sylvestre-Alvise, et al. "icarl: Incremental classifier and representation learning." CVPR 2017.


[IL2M] Belouadah, Eden, and Adrian Popescu. "Il2m: Class incremental learning with dual memory." ICCV 2019


[BiC] Wu, Yue, et al. "Large scale incremental learning." CVPR 2019.
• Training 후 Bias correction layer를 이용한
model output 수정
BiC (CVPR 2019)
• Old exemplar를 활용해 catastrophic
forgetting을 해결한 첫 시도
• Nearest Class Mean (NCM): old
exemplar의 average feature vector
를 이용해 class imbalance 보완
iCaRL (CVPR 2017) IL2M (ICCV 2019)
• Incremental Learning with
Dual Memory
• Dual Memory: old image &
과거 모델의 class statistics
• probability calibration
method
/ 23
2. Methods
1. Research Background 7
the main problem: the stability-plasticity dilemma
The	key	issue	of	CIL	is	that	the	models	trained	at	new	phases	easily	“forget”	old	classes.
0th-phase (n classes)
Old exemplars
New data
1st-phase (n+k classes) i-th-phase (n+ik classes)
D0
0th-model
Θ0
Sampling D0 ∋ ℰ0
Training
Old exemplars
New data
D1
1st-model
Θ1
Training
ℰ0
Old exemplars
New data
Di
i-th-model
Θi
Training
ℰ0:i−1 = {ℰ0, . . . , ℰi−1}
Old exemplar memory 제한으로 인한 class imbalance
Higher plasticity
- forgetting of old classes
Higher stability
- weakens the model from learning


the data of new classes
/ 23
2. Methods
2. Methods
2. Methods 9
Approach: Stable and Plastic Blocks
Plastic blocks: fully adopted to new class data
Stable blocks: partially fixed
Plasticity (새 class에 대한 학습) <-> Stability (old class knowledge를 잊지 않는)
More learnable parameter <-> Less learnable parameter
• We address the stability-plasticity dilemma by introducing a novel network architecture called
Adaptive Aggregation Networks (AANets).
/ 23
2. Methods
2. Methods 10
AANets: Stable and Plastic Blocks (Taking the ResNet as a baseline architectures)
Image
More learnable parameter ( ) <-> Less learnable parameter ( )
η ϕ
output features
classifier
contains all the convolutional weights <-> contains neuron-level scaling weights
η ϕ
• Contribution 1: a novel and generic network architecture called AANets
Plastic feature
Stable feature Aggregation weights
/ 23
2. Methods
2. Methods 11
bilevel optimization program (BOP)
Learning	rate:	0.1
ℰ0:i−1 = {ℰ0, . . . , ℰi−1}
Di ℰi
Lower-level	problem	training
/ 23
2. Methods
2. Methods 12
bilevel optimization program (BOP)
ℰ0:i−1 = {ℰ0, . . . , ℰi−1}
upper-level	problem	training
Learning	rate:	1 × 10−8
Di ℰi
• Contribution 2: a BOP-based formulation and an end-to-end training solution for optimizing AANets
/ 23
2. Methods
2. Methods 13
Previous works - Parameter-isolation-based methods in incremental learning
•Conditional Channel Gated Networks (Abati et al., CVPR 2020): conv layer 뒤에 task-specific gating module을 두고, 이
module이 새로운 task를 학습할 때 conv layer에서 어떤 filter를 적용할지 결정하게 함
•Random path selection for incremental learning (Rajasegaran et al., NeurIPS 2019): neural network을 module (conv-bn-
relu-conv-bn) 형태로 구성하고, new task에 대한 optimal path를 선택하도록 함
•Reinforced Continual Learning (Xu et al., NeurIPS 2018): 강화학습을 활용해 coming task에 가장 적합한 architecture를 탐색.
Conditional Channel Gated Networks Random path selection for incremental learning
/ 23
2. Methods
2. Methods 14
AANets: Stable and Plastic Blocks (Taking the ResNet as a baseline architectures)
Image
output features
Stable feature Aggregation weights
•AANets architecture:
•1 initial convolution layer -> 3 residual blocks (in a single branch) -> average-pooling -> fully connect layer.


각 block (level)은 10 conv layer (3 x 3 kernels) 로 구성. Filter 갯수는 16개로 시작해 다음 블록에서는 2배로 증가.
•Hyperparameter:
•Aggregation weights constraint:
•CIFAR-100 (ImageNet), we train the model for 160 (90) epochs in each phase, and the learning rates are divided by 10
after 80 (30) and then after 120 (60) epochs.
•SGD optimizer with the momentum 0.9, batch size 128 to train the models in all settings.
αη + αϕ = 1
/ 23
3. Experimental Results
2. Methods
3. Experimental Results 16
Experimental settings
•Data:
•CIFAR-100: 60,000 samples (32 x 32 color images for 100 classes). There are 500 training and 100 test samples for
each class (600 samples x 100 classes).
•ImageNet: 1.3 million samples (224 x 224 color images for 1000 classes). There are approximately 1,300 training and
50 test samples for each class. The 100-class data for ImageNet-Subset are sampled from ImageNet
N=5
50 class 10 c
0-th phase
10 c 10 c 10 c 10 c
1 ~ 5-th phase
50 class 5 c
0-th phase 1 ~ 10-th phase
5 c 5 c 5 c 5 c 5 c 5 c 5 c 5 c 5 c
N=10
•CIL settings example for CIFAR-100 & ImageNet-Subset:
/ 23
2. Methods
3. Experimental Results 17
“Stable block” + “Plastic block” approach의 성능 확인
“All” + “frozen” -> plastic block은 모든 weight를 학습시키고, stable block은 freeze 시켰다는 의미.
/ 23
2. Methods
3. Experimental Results 18
Ablation study
1) Balanced subset을 활용해 aggregation weights alpha를 학습하는 것이 성능에 중요한 영향을 미쳤다.
2) Memory overhead가 26%, 14.5% 감소한 것에 비해 성능 감소는 작았다. (CIFAR-100 N=5에서 0.3% 감소)
Row 6-8 setting: “all” + “frozen”
Row 6:
Row 7
Row 6
Row 8
Row 7: w/o adapted alpha:
Row 8: memory overhead 감소 (20 images / class -> 13, 16 images / class)
/ 23
2. Methods
3. Experimental Results 19
Comparing to the State-of-the-Art
/ 23
2. Methods
3. Experimental Results 20
Stable/plastic block의 역할을 class activation map을 통해 확인
•5-phase class incremental learning (ImageNet-Subset) 을 마친 후 최종 모델에 대해 실험
•과거 phase에 포함되어 있는 class에 해당하는 image를 어떻게 표시할지 확인
1) Stable block은 과거 phase에서 학습한 class, plastic block은 최근에 학습한 class의 지식을 잘 담고 있다.
2) 학습된 aggregation weights가 두 block의 지식을 잘 조율해 높은 성능을 만들었다.
/ 23
2. Methods
3. Experimental Results 21
Aggregation weights가 CIL과정에서 어떻게 변화하는지 확인
• 저자들은 Level 1 은 모든 class에서 공유할 수 있는 low-level feature를 encoding하기 때문에 새 class가 추가될
수록 plastic block feature의 비중이 높고, level 3는 classifier와 가까워 새로운 class를 학습한 plastic block
feature의 비중이 높다고 설명한다.
(stable block의 aggregation weight)
αϕ
(plastic block의 aggregation weight)
αη
/ 23
4. Conclusion
2. Methods
4. Conclusions 23
Thank you.
• 이 논문에서는 Class incremental learning에서의 catastrophic forgetting 문제를 해결
하기 위한 새로운 architecture AANets를 제시했다.
• Two types of residual block (Plastic block: learn plasticity, Stable block: learn stability)
을 따로 학습시켰다.
• 각 feature를 조합하는 최적의 aggregation weights를 learnable parameter로 두어 학습
시켰다.


• 새로 제시한 방법으로 ImageNet-1000, ImageNet-100, CIFAR-100에 대한 class
incremental learning task를 시도한 결과, 기존 CIL method보다 더 나은 성능을 보였다.


• AANets는 generic approach로서, 기존의 CIL method에 적용되어 성능을 높일 수 있다.
/ 23

More Related Content

What's hot

Deep Learning Fast MRI Using Channel Attention in Magnitude Domain
Deep Learning Fast MRI Using Channel Attention in Magnitude DomainDeep Learning Fast MRI Using Channel Attention in Magnitude Domain
Deep Learning Fast MRI Using Channel Attention in Magnitude DomainJoonhyung Lee
 
Deeplabv1, v2, v3, v3+
Deeplabv1, v2, v3, v3+Deeplabv1, v2, v3, v3+
Deeplabv1, v2, v3, v3+Sungchul Kim
 
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object DetectorPR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object DetectorJinwon Lee
 
PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transforme...
PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transforme...PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transforme...
PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transforme...Jinwon Lee
 
Vision Transformer(ViT) / An Image is Worth 16*16 Words: Transformers for Ima...
Vision Transformer(ViT) / An Image is Worth 16*16 Words: Transformers for Ima...Vision Transformer(ViT) / An Image is Worth 16*16 Words: Transformers for Ima...
Vision Transformer(ViT) / An Image is Worth 16*16 Words: Transformers for Ima...changedaeoh
 
PR-297: Training data-efficient image transformers & distillation through att...
PR-297: Training data-efficient image transformers & distillation through att...PR-297: Training data-efficient image transformers & distillation through att...
PR-297: Training data-efficient image transformers & distillation through att...Jinwon Lee
 
PR-305: Exploring Simple Siamese Representation Learning
PR-305: Exploring Simple Siamese Representation LearningPR-305: Exploring Simple Siamese Representation Learning
PR-305: Exploring Simple Siamese Representation LearningSungchul Kim
 
Multimodal Residual Learning for Visual QA
Multimodal Residual Learning for Visual QAMultimodal Residual Learning for Visual QA
Multimodal Residual Learning for Visual QANamHyuk Ahn
 
Review : Rethinking Pre-training and Self-training
Review : Rethinking Pre-training and Self-trainingReview : Rethinking Pre-training and Self-training
Review : Rethinking Pre-training and Self-trainingDongmin Choi
 
[PR12] PR-050: Convolutional LSTM Network: A Machine Learning Approach for Pr...
[PR12] PR-050: Convolutional LSTM Network: A Machine Learning Approach for Pr...[PR12] PR-050: Convolutional LSTM Network: A Machine Learning Approach for Pr...
[PR12] PR-050: Convolutional LSTM Network: A Machine Learning Approach for Pr...Taegyun Jeon
 
Adaptive Training of Radial Basis Function Networks Based on Cooperative
Adaptive Training of Radial Basis Function Networks Based on CooperativeAdaptive Training of Radial Basis Function Networks Based on Cooperative
Adaptive Training of Radial Basis Function Networks Based on CooperativeESCOM
 
Parn pyramidal+affine+regression+networks+for+dense+semantic+correspondence
Parn pyramidal+affine+regression+networks+for+dense+semantic+correspondenceParn pyramidal+affine+regression+networks+for+dense+semantic+correspondence
Parn pyramidal+affine+regression+networks+for+dense+semantic+correspondenceNAVER Engineering
 
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo SupervisionPR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo SupervisionSungchul Kim
 
Mlp mixer an all-mlp architecture for vision
Mlp mixer  an all-mlp architecture for visionMlp mixer  an all-mlp architecture for vision
Mlp mixer an all-mlp architecture for visionJaey Jeong
 
CNN and its applications by ketaki
CNN and its applications by ketakiCNN and its applications by ketaki
CNN and its applications by ketakiKetaki Patwari
 
YOLO9000 - PR023
YOLO9000 - PR023YOLO9000 - PR023
YOLO9000 - PR023Jinwon Lee
 
DeconvNet, DecoupledNet, TransferNet in Image Segmentation
DeconvNet, DecoupledNet, TransferNet in Image SegmentationDeconvNet, DecoupledNet, TransferNet in Image Segmentation
DeconvNet, DecoupledNet, TransferNet in Image SegmentationNamHyuk Ahn
 
PR-317: MLP-Mixer: An all-MLP Architecture for Vision
PR-317: MLP-Mixer: An all-MLP Architecture for VisionPR-317: MLP-Mixer: An all-MLP Architecture for Vision
PR-317: MLP-Mixer: An all-MLP Architecture for VisionJinwon Lee
 

What's hot (20)

Deep Learning Fast MRI Using Channel Attention in Magnitude Domain
Deep Learning Fast MRI Using Channel Attention in Magnitude DomainDeep Learning Fast MRI Using Channel Attention in Magnitude Domain
Deep Learning Fast MRI Using Channel Attention in Magnitude Domain
 
Deeplabv1, v2, v3, v3+
Deeplabv1, v2, v3, v3+Deeplabv1, v2, v3, v3+
Deeplabv1, v2, v3, v3+
 
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object DetectorPR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
 
PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transforme...
PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transforme...PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transforme...
PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transforme...
 
Vision Transformer(ViT) / An Image is Worth 16*16 Words: Transformers for Ima...
Vision Transformer(ViT) / An Image is Worth 16*16 Words: Transformers for Ima...Vision Transformer(ViT) / An Image is Worth 16*16 Words: Transformers for Ima...
Vision Transformer(ViT) / An Image is Worth 16*16 Words: Transformers for Ima...
 
PR-297: Training data-efficient image transformers & distillation through att...
PR-297: Training data-efficient image transformers & distillation through att...PR-297: Training data-efficient image transformers & distillation through att...
PR-297: Training data-efficient image transformers & distillation through att...
 
PR-305: Exploring Simple Siamese Representation Learning
PR-305: Exploring Simple Siamese Representation LearningPR-305: Exploring Simple Siamese Representation Learning
PR-305: Exploring Simple Siamese Representation Learning
 
Multimodal Residual Learning for Visual QA
Multimodal Residual Learning for Visual QAMultimodal Residual Learning for Visual QA
Multimodal Residual Learning for Visual QA
 
Review : Rethinking Pre-training and Self-training
Review : Rethinking Pre-training and Self-trainingReview : Rethinking Pre-training and Self-training
Review : Rethinking Pre-training and Self-training
 
[PR12] PR-050: Convolutional LSTM Network: A Machine Learning Approach for Pr...
[PR12] PR-050: Convolutional LSTM Network: A Machine Learning Approach for Pr...[PR12] PR-050: Convolutional LSTM Network: A Machine Learning Approach for Pr...
[PR12] PR-050: Convolutional LSTM Network: A Machine Learning Approach for Pr...
 
Adaptive Training of Radial Basis Function Networks Based on Cooperative
Adaptive Training of Radial Basis Function Networks Based on CooperativeAdaptive Training of Radial Basis Function Networks Based on Cooperative
Adaptive Training of Radial Basis Function Networks Based on Cooperative
 
Parn pyramidal+affine+regression+networks+for+dense+semantic+correspondence
Parn pyramidal+affine+regression+networks+for+dense+semantic+correspondenceParn pyramidal+affine+regression+networks+for+dense+semantic+correspondence
Parn pyramidal+affine+regression+networks+for+dense+semantic+correspondence
 
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo SupervisionPR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
 
Mlp mixer an all-mlp architecture for vision
Mlp mixer  an all-mlp architecture for visionMlp mixer  an all-mlp architecture for vision
Mlp mixer an all-mlp architecture for vision
 
2021 04-03-sean
2021 04-03-sean2021 04-03-sean
2021 04-03-sean
 
CNN and its applications by ketaki
CNN and its applications by ketakiCNN and its applications by ketaki
CNN and its applications by ketaki
 
YOLO9000 - PR023
YOLO9000 - PR023YOLO9000 - PR023
YOLO9000 - PR023
 
DeconvNet, DecoupledNet, TransferNet in Image Segmentation
DeconvNet, DecoupledNet, TransferNet in Image SegmentationDeconvNet, DecoupledNet, TransferNet in Image Segmentation
DeconvNet, DecoupledNet, TransferNet in Image Segmentation
 
PR-317: MLP-Mixer: An all-MLP Architecture for Vision
PR-317: MLP-Mixer: An all-MLP Architecture for VisionPR-317: MLP-Mixer: An all-MLP Architecture for Vision
PR-317: MLP-Mixer: An all-MLP Architecture for Vision
 
2020 12-03-vit
2020 12-03-vit2020 12-03-vit
2020 12-03-vit
 

Similar to PR-351: Adaptive Aggregation Networks for Class-Incremental Learning

UNetEliyaLaialy (2).pptx
UNetEliyaLaialy (2).pptxUNetEliyaLaialy (2).pptx
UNetEliyaLaialy (2).pptxNoorUlHaq47
 
Deep learning in Computer Vision
Deep learning in Computer VisionDeep learning in Computer Vision
Deep learning in Computer VisionDavid Dao
 
PR-393: ResLT: Residual Learning for Long-tailed Recognition
PR-393: ResLT: Residual Learning for Long-tailed RecognitionPR-393: ResLT: Residual Learning for Long-tailed Recognition
PR-393: ResLT: Residual Learning for Long-tailed RecognitionSunghoon Joo
 
A Review on Color Recognition using Deep Learning and Different Image Segment...
A Review on Color Recognition using Deep Learning and Different Image Segment...A Review on Color Recognition using Deep Learning and Different Image Segment...
A Review on Color Recognition using Deep Learning and Different Image Segment...IRJET Journal
 
Practical tips for handling noisy data and annotaiton
Practical tips for handling noisy data and annotaitonPractical tips for handling noisy data and annotaiton
Practical tips for handling noisy data and annotaitonRyuichiKanoh
 
Network Recasting: A Universal Method for Network Architecture Transformation
Network Recasting: A Universal Method for Network Architecture TransformationNetwork Recasting: A Universal Method for Network Architecture Transformation
Network Recasting: A Universal Method for Network Architecture TransformationJoonsangYu2
 
Detection focal loss 딥러닝 논문읽기 모임 발표자료
Detection focal loss 딥러닝 논문읽기 모임 발표자료Detection focal loss 딥러닝 논문읽기 모임 발표자료
Detection focal loss 딥러닝 논문읽기 모임 발표자료taeseon ryu
 
Master defence 2020 -Volodymyr Lut-Neural Architecture Search: a Probabilisti...
Master defence 2020 -Volodymyr Lut-Neural Architecture Search: a Probabilisti...Master defence 2020 -Volodymyr Lut-Neural Architecture Search: a Probabilisti...
Master defence 2020 -Volodymyr Lut-Neural Architecture Search: a Probabilisti...Lviv Data Science Summer School
 
Waste Classification System using Convolutional Neural Networks.pptx
Waste Classification System using Convolutional Neural Networks.pptxWaste Classification System using Convolutional Neural Networks.pptx
Waste Classification System using Convolutional Neural Networks.pptxJohnPrasad14
 
A Review on Food Classification using Convolutional Neural Networks
A Review on Food Classification using Convolutional Neural NetworksA Review on Food Classification using Convolutional Neural Networks
A Review on Food Classification using Convolutional Neural NetworksIRJET Journal
 
4 high performance large-scale image recognition without normalization
4 high performance large-scale image recognition without normalization4 high performance large-scale image recognition without normalization
4 high performance large-scale image recognition without normalizationDonghoon Park
 
CNNs: from the Basics to Recent Advances
CNNs: from the Basics to Recent AdvancesCNNs: from the Basics to Recent Advances
CNNs: from the Basics to Recent AdvancesDmytro Mishkin
 
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...Universitat Politècnica de Catalunya
 
2017 (albawi-alkabi)image-net classification with deep convolutional neural n...
2017 (albawi-alkabi)image-net classification with deep convolutional neural n...2017 (albawi-alkabi)image-net classification with deep convolutional neural n...
2017 (albawi-alkabi)image-net classification with deep convolutional neural n...ali hassan
 
Basic Learning Algorithms of ANN
Basic Learning Algorithms of ANNBasic Learning Algorithms of ANN
Basic Learning Algorithms of ANNwaseem khan
 
Transfer learning with multiple pre-trained network for fundus classification
Transfer learning with multiple pre-trained network for fundus classificationTransfer learning with multiple pre-trained network for fundus classification
Transfer learning with multiple pre-trained network for fundus classificationTELKOMNIKA JOURNAL
 
Using Multi-layered Feed-forward Neural Network (MLFNN) Architecture as Bidir...
Using Multi-layered Feed-forward Neural Network (MLFNN) Architecture as Bidir...Using Multi-layered Feed-forward Neural Network (MLFNN) Architecture as Bidir...
Using Multi-layered Feed-forward Neural Network (MLFNN) Architecture as Bidir...IOSR Journals
 

Similar to PR-351: Adaptive Aggregation Networks for Class-Incremental Learning (20)

UNetEliyaLaialy (2).pptx
UNetEliyaLaialy (2).pptxUNetEliyaLaialy (2).pptx
UNetEliyaLaialy (2).pptx
 
Deep learning in Computer Vision
Deep learning in Computer VisionDeep learning in Computer Vision
Deep learning in Computer Vision
 
PR-393: ResLT: Residual Learning for Long-tailed Recognition
PR-393: ResLT: Residual Learning for Long-tailed RecognitionPR-393: ResLT: Residual Learning for Long-tailed Recognition
PR-393: ResLT: Residual Learning for Long-tailed Recognition
 
A Review on Color Recognition using Deep Learning and Different Image Segment...
A Review on Color Recognition using Deep Learning and Different Image Segment...A Review on Color Recognition using Deep Learning and Different Image Segment...
A Review on Color Recognition using Deep Learning and Different Image Segment...
 
Practical tips for handling noisy data and annotaiton
Practical tips for handling noisy data and annotaitonPractical tips for handling noisy data and annotaiton
Practical tips for handling noisy data and annotaiton
 
Network Recasting: A Universal Method for Network Architecture Transformation
Network Recasting: A Universal Method for Network Architecture TransformationNetwork Recasting: A Universal Method for Network Architecture Transformation
Network Recasting: A Universal Method for Network Architecture Transformation
 
Detection focal loss 딥러닝 논문읽기 모임 발표자료
Detection focal loss 딥러닝 논문읽기 모임 발표자료Detection focal loss 딥러닝 논문읽기 모임 발표자료
Detection focal loss 딥러닝 논문읽기 모임 발표자료
 
Master defence 2020 -Volodymyr Lut-Neural Architecture Search: a Probabilisti...
Master defence 2020 -Volodymyr Lut-Neural Architecture Search: a Probabilisti...Master defence 2020 -Volodymyr Lut-Neural Architecture Search: a Probabilisti...
Master defence 2020 -Volodymyr Lut-Neural Architecture Search: a Probabilisti...
 
Waste Classification System using Convolutional Neural Networks.pptx
Waste Classification System using Convolutional Neural Networks.pptxWaste Classification System using Convolutional Neural Networks.pptx
Waste Classification System using Convolutional Neural Networks.pptx
 
Deep learning
Deep learningDeep learning
Deep learning
 
N ns 1
N ns 1N ns 1
N ns 1
 
A Review on Food Classification using Convolutional Neural Networks
A Review on Food Classification using Convolutional Neural NetworksA Review on Food Classification using Convolutional Neural Networks
A Review on Food Classification using Convolutional Neural Networks
 
Unit ii supervised ii
Unit ii supervised iiUnit ii supervised ii
Unit ii supervised ii
 
4 high performance large-scale image recognition without normalization
4 high performance large-scale image recognition without normalization4 high performance large-scale image recognition without normalization
4 high performance large-scale image recognition without normalization
 
CNNs: from the Basics to Recent Advances
CNNs: from the Basics to Recent AdvancesCNNs: from the Basics to Recent Advances
CNNs: from the Basics to Recent Advances
 
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
 
2017 (albawi-alkabi)image-net classification with deep convolutional neural n...
2017 (albawi-alkabi)image-net classification with deep convolutional neural n...2017 (albawi-alkabi)image-net classification with deep convolutional neural n...
2017 (albawi-alkabi)image-net classification with deep convolutional neural n...
 
Basic Learning Algorithms of ANN
Basic Learning Algorithms of ANNBasic Learning Algorithms of ANN
Basic Learning Algorithms of ANN
 
Transfer learning with multiple pre-trained network for fundus classification
Transfer learning with multiple pre-trained network for fundus classificationTransfer learning with multiple pre-trained network for fundus classification
Transfer learning with multiple pre-trained network for fundus classification
 
Using Multi-layered Feed-forward Neural Network (MLFNN) Architecture as Bidir...
Using Multi-layered Feed-forward Neural Network (MLFNN) Architecture as Bidir...Using Multi-layered Feed-forward Neural Network (MLFNN) Architecture as Bidir...
Using Multi-layered Feed-forward Neural Network (MLFNN) Architecture as Bidir...
 

More from Sunghoon Joo

PR-445: Token Merging: Your ViT But Faster
PR-445: Token Merging: Your ViT But FasterPR-445: Token Merging: Your ViT But Faster
PR-445: Token Merging: Your ViT But FasterSunghoon Joo
 
PR-433: Test-time Training with Masked Autoencoders
PR-433: Test-time Training with Masked AutoencodersPR-433: Test-time Training with Masked Autoencoders
PR-433: Test-time Training with Masked AutoencodersSunghoon Joo
 
PR422_hyper-deep ensembles.pdf
PR422_hyper-deep ensembles.pdfPR422_hyper-deep ensembles.pdf
PR422_hyper-deep ensembles.pdfSunghoon Joo
 
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...PR-411: Model soups: averaging weights of multiple fine-tuned models improves...
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...Sunghoon Joo
 
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...Sunghoon Joo
 
PR-339: Maintaining discrimination and fairness in class incremental learning
PR-339: Maintaining discrimination and fairness in class incremental learningPR-339: Maintaining discrimination and fairness in class incremental learning
PR-339: Maintaining discrimination and fairness in class incremental learningSunghoon Joo
 
PR-313 Training BatchNorm and Only BatchNorm: On the Expressive Power of Rand...
PR-313 Training BatchNorm and Only BatchNorm: On the Expressive Power of Rand...PR-313 Training BatchNorm and Only BatchNorm: On the Expressive Power of Rand...
PR-313 Training BatchNorm and Only BatchNorm: On the Expressive Power of Rand...Sunghoon Joo
 
PR-298 PARADE: Passage representation aggregation for document reranking
PR-298 PARADE: Passage representation aggregation for document rerankingPR-298 PARADE: Passage representation aggregation for document reranking
PR-298 PARADE: Passage representation aggregation for document rerankingSunghoon Joo
 
PR-285 Leveraging Semantic and Lexical Matching to Improve the Recall of Docu...
PR-285 Leveraging Semantic and Lexical Matching to Improve the Recall of Docu...PR-285 Leveraging Semantic and Lexical Matching to Improve the Recall of Docu...
PR-285 Leveraging Semantic and Lexical Matching to Improve the Recall of Docu...Sunghoon Joo
 
PR-272: Accelerating Large-Scale Inference with Anisotropic Vector Quantization
PR-272: Accelerating Large-Scale Inference with Anisotropic Vector QuantizationPR-272: Accelerating Large-Scale Inference with Anisotropic Vector Quantization
PR-272: Accelerating Large-Scale Inference with Anisotropic Vector QuantizationSunghoon Joo
 
PR-246: A deep learning system for differential diagnosis of skin diseases
PR-246: A deep learning system for differential diagnosis of skin diseasesPR-246: A deep learning system for differential diagnosis of skin diseases
PR-246: A deep learning system for differential diagnosis of skin diseasesSunghoon Joo
 
PR-218: MFAS: Multimodal Fusion Architecture Search
PR-218: MFAS: Multimodal Fusion Architecture SearchPR-218: MFAS: Multimodal Fusion Architecture Search
PR-218: MFAS: Multimodal Fusion Architecture SearchSunghoon Joo
 
PR-203: Class-Balanced Loss Based on Effective Number of Samples
PR-203: Class-Balanced Loss Based on Effective Number of SamplesPR-203: Class-Balanced Loss Based on Effective Number of Samples
PR-203: Class-Balanced Loss Based on Effective Number of SamplesSunghoon Joo
 
PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of D...
PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of D...PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of D...
PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of D...Sunghoon Joo
 
PR173 : Automatic Chemical Design Using a Data-Driven Continuous Representati...
PR173 : Automatic Chemical Design Using a Data-Driven Continuous Representati...PR173 : Automatic Chemical Design Using a Data-Driven Continuous Representati...
PR173 : Automatic Chemical Design Using a Data-Driven Continuous Representati...Sunghoon Joo
 
PR-159 : Synergistic Image and Feature Adaptation: Towards Cross-Modality Dom...
PR-159 : Synergistic Image and Feature Adaptation: Towards Cross-Modality Dom...PR-159 : Synergistic Image and Feature Adaptation: Towards Cross-Modality Dom...
PR-159 : Synergistic Image and Feature Adaptation: Towards Cross-Modality Dom...Sunghoon Joo
 

More from Sunghoon Joo (16)

PR-445: Token Merging: Your ViT But Faster
PR-445: Token Merging: Your ViT But FasterPR-445: Token Merging: Your ViT But Faster
PR-445: Token Merging: Your ViT But Faster
 
PR-433: Test-time Training with Masked Autoencoders
PR-433: Test-time Training with Masked AutoencodersPR-433: Test-time Training with Masked Autoencoders
PR-433: Test-time Training with Masked Autoencoders
 
PR422_hyper-deep ensembles.pdf
PR422_hyper-deep ensembles.pdfPR422_hyper-deep ensembles.pdf
PR422_hyper-deep ensembles.pdf
 
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...PR-411: Model soups: averaging weights of multiple fine-tuned models improves...
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...
 
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...
 
PR-339: Maintaining discrimination and fairness in class incremental learning
PR-339: Maintaining discrimination and fairness in class incremental learningPR-339: Maintaining discrimination and fairness in class incremental learning
PR-339: Maintaining discrimination and fairness in class incremental learning
 
PR-313 Training BatchNorm and Only BatchNorm: On the Expressive Power of Rand...
PR-313 Training BatchNorm and Only BatchNorm: On the Expressive Power of Rand...PR-313 Training BatchNorm and Only BatchNorm: On the Expressive Power of Rand...
PR-313 Training BatchNorm and Only BatchNorm: On the Expressive Power of Rand...
 
PR-298 PARADE: Passage representation aggregation for document reranking
PR-298 PARADE: Passage representation aggregation for document rerankingPR-298 PARADE: Passage representation aggregation for document reranking
PR-298 PARADE: Passage representation aggregation for document reranking
 
PR-285 Leveraging Semantic and Lexical Matching to Improve the Recall of Docu...
PR-285 Leveraging Semantic and Lexical Matching to Improve the Recall of Docu...PR-285 Leveraging Semantic and Lexical Matching to Improve the Recall of Docu...
PR-285 Leveraging Semantic and Lexical Matching to Improve the Recall of Docu...
 
PR-272: Accelerating Large-Scale Inference with Anisotropic Vector Quantization
PR-272: Accelerating Large-Scale Inference with Anisotropic Vector QuantizationPR-272: Accelerating Large-Scale Inference with Anisotropic Vector Quantization
PR-272: Accelerating Large-Scale Inference with Anisotropic Vector Quantization
 
PR-246: A deep learning system for differential diagnosis of skin diseases
PR-246: A deep learning system for differential diagnosis of skin diseasesPR-246: A deep learning system for differential diagnosis of skin diseases
PR-246: A deep learning system for differential diagnosis of skin diseases
 
PR-218: MFAS: Multimodal Fusion Architecture Search
PR-218: MFAS: Multimodal Fusion Architecture SearchPR-218: MFAS: Multimodal Fusion Architecture Search
PR-218: MFAS: Multimodal Fusion Architecture Search
 
PR-203: Class-Balanced Loss Based on Effective Number of Samples
PR-203: Class-Balanced Loss Based on Effective Number of SamplesPR-203: Class-Balanced Loss Based on Effective Number of Samples
PR-203: Class-Balanced Loss Based on Effective Number of Samples
 
PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of D...
PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of D...PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of D...
PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of D...
 
PR173 : Automatic Chemical Design Using a Data-Driven Continuous Representati...
PR173 : Automatic Chemical Design Using a Data-Driven Continuous Representati...PR173 : Automatic Chemical Design Using a Data-Driven Continuous Representati...
PR173 : Automatic Chemical Design Using a Data-Driven Continuous Representati...
 
PR-159 : Synergistic Image and Feature Adaptation: Towards Cross-Modality Dom...
PR-159 : Synergistic Image and Feature Adaptation: Towards Cross-Modality Dom...PR-159 : Synergistic Image and Feature Adaptation: Towards Cross-Modality Dom...
PR-159 : Synergistic Image and Feature Adaptation: Towards Cross-Modality Dom...
 

Recently uploaded

Software Development Life Cycle By Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By  Team Orange (Dept. of Pharmacy)Software Development Life Cycle By  Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By Team Orange (Dept. of Pharmacy)Suman Mia
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Christo Ananth
 
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130Suhani Kapoor
 
Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)simmis5
 
Microscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxMicroscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxpurnimasatapathy1234
 
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...roncy bisnoi
 
Extrusion Processes and Their Limitations
Extrusion Processes and Their LimitationsExtrusion Processes and Their Limitations
Extrusion Processes and Their Limitations120cr0395
 
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escortsranjana rawat
 
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls in Nagpur High Profile
 
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Christo Ananth
 
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur High Profile
 
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...ranjana rawat
 
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...Dr.Costas Sachpazis
 
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Serviceranjana rawat
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSISrknatarajan
 
Coefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxCoefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxAsutosh Ranjan
 
247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt
247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt
247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).pptssuser5c9d4b1
 
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordCCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordAsst.prof M.Gokilavani
 

Recently uploaded (20)

Software Development Life Cycle By Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By  Team Orange (Dept. of Pharmacy)Software Development Life Cycle By  Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By Team Orange (Dept. of Pharmacy)
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
 
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
 
Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)
 
Microscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxMicroscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptx
 
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
 
Extrusion Processes and Their Limitations
Extrusion Processes and Their LimitationsExtrusion Processes and Their Limitations
Extrusion Processes and Their Limitations
 
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
 
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
 
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
 
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
 
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
 
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
 
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
 
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINEDJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSIS
 
Coefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxCoefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptx
 
247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt
247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt
247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt
 
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordCCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
 

PR-351: Adaptive Aggregation Networks for Class-Incremental Learning

  • 1. CVPR 202 0 주성훈, VUNO Inc. 2021. 10. 17. PR-351
  • 3. 2. Methods 1. Research Background 3 Class incremental learning 많은 real-world application에서, streaming data로부터 점진적으로 새로운 class들을 학습해야 하는 경우가 있는데, 이를 class incremental learning이라고 한다. Incremental learning aims to learn efficient machine models from the data that gradually come in a sequence of training phases. Closely related topics are referred to as continual learning and lifelong learning. Xiao, Tianjun, et al. "Error-driven incremental learning in deep convolutional neural network for large-scale image classification." Proceedings of the 22nd ACM international conference on Multimedia. 2014. / 23
  • 4. 2. Methods 1. Research Background 4 • 새로운 incremental phase에서 학습된 모델은 old class를 쉽게 잊는다 Motivation - catastrophic forgetting issue / 23
  • 5. 2. Methods 1. Research Background 5 (Recap from PR-339) Previous works - Replay based method Old data에 대한 additional memory를 만들고, 이를 활용해 catastrophic forgetting을 막는다. IL2M (ICCV 2019) Figure from: Belouadah, Eden, and Adrian Popescu. "Il2m: Class incremental learning with dual memory." ICCV 2019. / 23
  • 6. 2. Methods 1. Research Background 6 (Recap from PR-339) Previous works - Replay based method Old data에 대한 additional memory를 만들고, 이를 활용해 catastrophic forgetting을 막는다. [iCaRL] Rebuffi, Sylvestre-Alvise, et al. "icarl: Incremental classifier and representation learning." CVPR 2017. [IL2M] Belouadah, Eden, and Adrian Popescu. "Il2m: Class incremental learning with dual memory." ICCV 2019 [BiC] Wu, Yue, et al. "Large scale incremental learning." CVPR 2019. • Training 후 Bias correction layer를 이용한 model output 수정 BiC (CVPR 2019) • Old exemplar를 활용해 catastrophic forgetting을 해결한 첫 시도 • Nearest Class Mean (NCM): old exemplar의 average feature vector 를 이용해 class imbalance 보완 iCaRL (CVPR 2017) IL2M (ICCV 2019) • Incremental Learning with Dual Memory • Dual Memory: old image & 과거 모델의 class statistics • probability calibration method / 23
  • 7. 2. Methods 1. Research Background 7 the main problem: the stability-plasticity dilemma The key issue of CIL is that the models trained at new phases easily “forget” old classes. 0th-phase (n classes) Old exemplars New data 1st-phase (n+k classes) i-th-phase (n+ik classes) D0 0th-model Θ0 Sampling D0 ∋ ℰ0 Training Old exemplars New data D1 1st-model Θ1 Training ℰ0 Old exemplars New data Di i-th-model Θi Training ℰ0:i−1 = {ℰ0, . . . , ℰi−1} Old exemplar memory 제한으로 인한 class imbalance Higher plasticity - forgetting of old classes Higher stability - weakens the model from learning 
 the data of new classes / 23
  • 9. 2. Methods 2. Methods 9 Approach: Stable and Plastic Blocks Plastic blocks: fully adopted to new class data Stable blocks: partially fixed Plasticity (새 class에 대한 학습) <-> Stability (old class knowledge를 잊지 않는) More learnable parameter <-> Less learnable parameter • We address the stability-plasticity dilemma by introducing a novel network architecture called Adaptive Aggregation Networks (AANets). / 23
  • 10. 2. Methods 2. Methods 10 AANets: Stable and Plastic Blocks (Taking the ResNet as a baseline architectures) Image More learnable parameter ( ) <-> Less learnable parameter ( ) η ϕ output features classifier contains all the convolutional weights <-> contains neuron-level scaling weights η ϕ • Contribution 1: a novel and generic network architecture called AANets Plastic feature Stable feature Aggregation weights / 23
  • 11. 2. Methods 2. Methods 11 bilevel optimization program (BOP) Learning rate: 0.1 ℰ0:i−1 = {ℰ0, . . . , ℰi−1} Di ℰi Lower-level problem training / 23
  • 12. 2. Methods 2. Methods 12 bilevel optimization program (BOP) ℰ0:i−1 = {ℰ0, . . . , ℰi−1} upper-level problem training Learning rate: 1 × 10−8 Di ℰi • Contribution 2: a BOP-based formulation and an end-to-end training solution for optimizing AANets / 23
  • 13. 2. Methods 2. Methods 13 Previous works - Parameter-isolation-based methods in incremental learning •Conditional Channel Gated Networks (Abati et al., CVPR 2020): conv layer 뒤에 task-specific gating module을 두고, 이 module이 새로운 task를 학습할 때 conv layer에서 어떤 filter를 적용할지 결정하게 함 •Random path selection for incremental learning (Rajasegaran et al., NeurIPS 2019): neural network을 module (conv-bn- relu-conv-bn) 형태로 구성하고, new task에 대한 optimal path를 선택하도록 함 •Reinforced Continual Learning (Xu et al., NeurIPS 2018): 강화학습을 활용해 coming task에 가장 적합한 architecture를 탐색. Conditional Channel Gated Networks Random path selection for incremental learning / 23
  • 14. 2. Methods 2. Methods 14 AANets: Stable and Plastic Blocks (Taking the ResNet as a baseline architectures) Image output features Stable feature Aggregation weights •AANets architecture: •1 initial convolution layer -> 3 residual blocks (in a single branch) -> average-pooling -> fully connect layer. 
 각 block (level)은 10 conv layer (3 x 3 kernels) 로 구성. Filter 갯수는 16개로 시작해 다음 블록에서는 2배로 증가. •Hyperparameter: •Aggregation weights constraint: •CIFAR-100 (ImageNet), we train the model for 160 (90) epochs in each phase, and the learning rates are divided by 10 after 80 (30) and then after 120 (60) epochs. •SGD optimizer with the momentum 0.9, batch size 128 to train the models in all settings. αη + αϕ = 1 / 23
  • 16. 2. Methods 3. Experimental Results 16 Experimental settings •Data: •CIFAR-100: 60,000 samples (32 x 32 color images for 100 classes). There are 500 training and 100 test samples for each class (600 samples x 100 classes). •ImageNet: 1.3 million samples (224 x 224 color images for 1000 classes). There are approximately 1,300 training and 50 test samples for each class. The 100-class data for ImageNet-Subset are sampled from ImageNet N=5 50 class 10 c 0-th phase 10 c 10 c 10 c 10 c 1 ~ 5-th phase 50 class 5 c 0-th phase 1 ~ 10-th phase 5 c 5 c 5 c 5 c 5 c 5 c 5 c 5 c 5 c N=10 •CIL settings example for CIFAR-100 & ImageNet-Subset: / 23
  • 17. 2. Methods 3. Experimental Results 17 “Stable block” + “Plastic block” approach의 성능 확인 “All” + “frozen” -> plastic block은 모든 weight를 학습시키고, stable block은 freeze 시켰다는 의미. / 23
  • 18. 2. Methods 3. Experimental Results 18 Ablation study 1) Balanced subset을 활용해 aggregation weights alpha를 학습하는 것이 성능에 중요한 영향을 미쳤다. 2) Memory overhead가 26%, 14.5% 감소한 것에 비해 성능 감소는 작았다. (CIFAR-100 N=5에서 0.3% 감소) Row 6-8 setting: “all” + “frozen” Row 6: Row 7 Row 6 Row 8 Row 7: w/o adapted alpha: Row 8: memory overhead 감소 (20 images / class -> 13, 16 images / class) / 23
  • 19. 2. Methods 3. Experimental Results 19 Comparing to the State-of-the-Art / 23
  • 20. 2. Methods 3. Experimental Results 20 Stable/plastic block의 역할을 class activation map을 통해 확인 •5-phase class incremental learning (ImageNet-Subset) 을 마친 후 최종 모델에 대해 실험 •과거 phase에 포함되어 있는 class에 해당하는 image를 어떻게 표시할지 확인 1) Stable block은 과거 phase에서 학습한 class, plastic block은 최근에 학습한 class의 지식을 잘 담고 있다. 2) 학습된 aggregation weights가 두 block의 지식을 잘 조율해 높은 성능을 만들었다. / 23
  • 21. 2. Methods 3. Experimental Results 21 Aggregation weights가 CIL과정에서 어떻게 변화하는지 확인 • 저자들은 Level 1 은 모든 class에서 공유할 수 있는 low-level feature를 encoding하기 때문에 새 class가 추가될 수록 plastic block feature의 비중이 높고, level 3는 classifier와 가까워 새로운 class를 학습한 plastic block feature의 비중이 높다고 설명한다. (stable block의 aggregation weight) αϕ (plastic block의 aggregation weight) αη / 23
  • 23. 2. Methods 4. Conclusions 23 Thank you. • 이 논문에서는 Class incremental learning에서의 catastrophic forgetting 문제를 해결 하기 위한 새로운 architecture AANets를 제시했다. • Two types of residual block (Plastic block: learn plasticity, Stable block: learn stability) 을 따로 학습시켰다. • 각 feature를 조합하는 최적의 aggregation weights를 learnable parameter로 두어 학습 시켰다. 
 • 새로 제시한 방법으로 ImageNet-1000, ImageNet-100, CIFAR-100에 대한 class incremental learning task를 시도한 결과, 기존 CIL method보다 더 나은 성능을 보였다. 
 • AANets는 generic approach로서, 기존의 CIL method에 적용되어 성능을 높일 수 있다. / 23