SlideShare a Scribd company logo
1 of 36
IntroductiontosomeDifferentkindsofGAN
Parham Zilouchian
Seminar, Winter 2021
Dr. Ahmad Khonsari
Outline
• Part 1: Introduction to GANs
• Part 2: Applications of GANs
• Part 3: Project Introduction
2
Introduction to
GANs
Let’s dive in
GANs
• Generative
• Learn a generative model
• Adversarial
• Trained in an adversarial setting
• Networks
• Use Deep Neural Networks
4
Generative Adversarial Networks
(Ian J. Goodfellow, 10 Jun 2014)
5
 Two components, the generator and the discriminator:
 The generator G needs to capture the data distribution.
 The discriminator D estimates the probability that a sample comes from the training
data rather than from G.
• The discriminator in a GAN is simply a classifier.
• It tries to distinguish real data from the data created by the generator.
• It could use any network architecture appropriate to the type of data it’s classifying.
The Discriminator
1
2
3
6
The Generator
7
1. Produce generator output from sampled random noise.
2. Get discriminator "Real" or "Fake" classification for generator output.
3. Calculate loss from discriminator classification.
4. Backpropagate through both the discriminator and generator to obtain gradients.
5. Use gradients to change only the generator weights.
1
2
3
4
5
8
Overview of GAN Structure
GANs – Training
9
Why Generative Models?
 We’ve only seen discriminative models so far
• Given an image X, predict a label Y
• Estimates P(Y|X)
Discriminative models have several key limitations
• Can’t model P(X), i.e. the probability of seeing a certain image
• • Thus, can’t sample from P(X), i.e. can’t generate new images
Generative models (in general) cope with all of above
• Can model P(X)
• Can generate new images
• We can use these new images for lack of enough data.
10
Semi – Supervised GANs (5 Jun 2016, Augustus Odena)
11
• In Normal GANs we train both Generator & Discriminator at the same time. / after training we discard the discriminator
because we used it just for training the Generator.
• For semi-supervised learning, we need to transform the discriminator into a multi-class classifier.
• for each input image, the discriminator has to learn the probabilities of it being a one, two, three and so on.
• Help the Generator to produce realistic images ⇒ we have to instruct the Discriminator to distinguish between real / fake
samples.
• Use the Generator’s Images, along with the labeled &
Unlabeled training data, to help classify the dataset.
1
2
3
4
5
Semi – Supervised GANs VS. Normal GANs
12
96.4
92.8
88.3
80.2
96.5
89.5
85.9
75
0
10
20
30
40
50
60
70
80
90
100
1000 Sample 100 Sample 50 Sample 25 Sample
Model
Accuracy
# of Samples
Compare Accuracy of training with different # of samples
SGAN GAN
What is DCGAN? (19 Nov 2015 , Alec Radford)
 DCGAN: Deep Convolutional Generative Adversarial Networks
 It works in the opposite direction of the image classifier (CNN).
 CNN transforms an image to a class label (list of probabilities).
 DCGAN generates an image from random parameters.
13
Training Strategy of DCGAN
 We train two models simultaneously.
 CNN: Classifying authentic and fake images.
 "Authentic" images are provided as training data to CNN.
 DCGAN: Trained to generate images classified as authentic by CNN.
 By trying to fool CNN, DCGAN learns to generate images similar to the training data.
14
Training Loop of DCGAN
15
P(A) : Probability that A is
authentic.
P(B) : Probability that B is
authentic.
By repeating this loop, CNN becomes
more accurate and DCGAN becomes
more crafty.
DCGAN
16
Latent vectors capture interesting patterns…
17
Radford, Alec, Luke Metz, and Soumith Chintala. "Unsupervised representation learning with deep convolutional generative adversarial networks." arXiv:1511.06434 (2015).
STAR GAN (24 Nov 2017, Yunjey Choi)
18
STAR GAN Structure
19
FT GAN (19 July 2019, Weiwei Zhuang)
20
FT GAN Structure
21
22
Character
GAN
5 Feb 2021
Tobias Hinz
Character GAN
23
 Character GAN: a generative model that can be trained on only a few samples (8 – 15) of a
given character.
 We train a generative model in a low-data setting (8 to 15 training samples) to repose &
animate characters based on keypoint positions.
 This model generates novel poses based on keypoint locations.
Character GAN
24
• Since we only have limited training samples, one of the key challenges lies in how to address (dis)occlusion. e.g. when a
hand moves behind or in front of a body.
• To address mentioned problem we introduce a novel layering approach which explicitly splits the input keypoints into
different layers which are processed independently.
• These layers represent different parts of the character and provide a strong implicit bias that helps to obtain realistic
results even with strong (dis)occlusions.
• To combine the features of individual layers ⇒ we use an adaptive scaling approach conditioned on all keypoints.
• This model scales to larger datasets when more data is available.
1
2
3
4
5
Character GAN
25
• (Problem) If some body parts are occluded by others they still exist even though
they may not be visible. ⇒ we split our characters into different layers (Solve).
• To model different layers, the generator processes each keypoint individually and learns a representation
of each keypoint layer.
• Adaptive scaling technique: ⇒ we scale the features of each layer before concatenating them!
• For AST we first learn an embedding of the keypoints & their layers. ⇔ Based on this embedding we then
learn scaling parameters for each keypoint layer & use them to scale the features of each layer.
1
2
3
4
5
• Model:
Generator: ⇒ generates the image based on the keypoint location.
Discriminator: ⇒ trained to distinguish between real & fake image-keypoint pairs.
Character GAN - Layering
1
2
3
4
• our layered approach is beneficial when several
keypoints overlap in the 2D space,
• e.g. representing the “left” side of the character
(e.g. left arm and leg), the “middle” part of the
character (e.g. head and torso) and the “right” side
of the character (e.g. right arm and leg).
• These layers can be modeled individually and can
then be composed to form a final image.
• To model this, our generator processes each
keypoint layer individually and learns a
representation of each keypoint layer.
26
Character GAN – Patch Based Refinement
1
2
3
4
• To further improve the final result we apply a patch-based refinement
algorithm that replaces generated patches with their closest real patch.
• In our case, given a real & a generated image, for each patch in the
generated image, we find the closest patch in the dataset.
• We use Patch Match approximation nearest neighbor algorithm: ⇒ Replace
the generated patches with their real equivalent.
• This approach often improves the sharpness and general image quality over
the output of the generator.
27
28
Bionic Eye
29
Bionic Eye Structure
Construct a combination of Gan Models introduced.
Optimize it for Low-Complexity
Create a creativity based GAN application
Lunch it as an Experimental product
Steps Ahead
30
31
Our System Summary
31
• [1] Goodfellow, I., et al.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D.,
Weinberger, K.Q. (eds.) NIPS 2014, pp. 2672–2680 (2014)
• [2] Bengio, Y. (2009). Learning deep architectures for AI. Now Publishers.
• [3] Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative
adversarial networks. In: ICLR 2016 (2016)
• [4] Hinton, G., Deng, L., Dahl, G. E., Mohamed, A., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T.,
and Kingsbury, B. (2012a). Deep neural networks for acoustic modeling in speech recognition. IEEE Signal
Processing Magazine, 29(6), 82–97.
• [5] Krizhevsky, A., Sutskever, I., and Hinton, G. (2012). ImageNet classification with deep convolutional neural
networks. In NIPS’2012.
• [6] Jarrett, K., Kavukcuoglu, K., Ranzato, M., and LeCun, Y. (2009). What is the best multi-stage architecture for
object recognition? In Proc. International Conference on Computer Vision (ICCV’09), pages 2146–2153. IEEE.
• [7] Goodfellow, I. J., Mirza, M., Courville, A., and Bengio, Y. (2013b). Multi-prediction deep Boltzmann machines.
In NIPS’2013.
• [8] Hinz, T., Fisher, M., Wang, O., Shechtman, E., and Wermter, S., “CharacterGAN: Few-Shot Keypoint Character
Animation and Reposing”, 2021. Link: https://arxiv.org/abs/2102.03141
Resources
32
• [9] Choi, H., Park, C. and Lee, K., 2020. From Inference To Generation: End-To-End Fully Self-Supervised Generation Of Human
Face From Speech.
• [10] Odena, Augustus. “Semi-Supervised Learning with Generative Adversarial Networks.” ArXiv abs/1606.01583 (2016): n. pag.
• [11] Chen, Xiang et al. “FTGAN: A Fully-trained Generative Adversarial Networks for Text to Face
Generation.” ArXiv abs/1904.05729 (2019): n. pag.
• [12] Y. Choi, M. Choi, M. Kim, J. Ha, S. Kim and J. Choo, "StarGAN: Unified Generative Adversarial Networks for Multi-domain
Image-to-Image Translation," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, 2018,
pp. 8789-8797, doi: 10.1109/CVPR.2018.00916.
• [13] K. Kumar, R. Kumar, T. de Boissiere, L. Gestin, W. Z. Teoh, J. Sotelo, A. de Brebisson, Y. Bengio, and A. Courville,
“MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis,” arXiv.org, 09-Dec-2019.
• [14] S. Palazzo, C. Spampinato, I. Kavasidis, D. Giordano and M. Shah, "Generative Adversarial Networks
Conditioned by Brain Signals," in 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy
• [15] Shimizu T., Xu J., Tasaka K. (2020) MobileGAN: Compact Network Architecture for Generative Adversarial
Network. In: Palaiahnakote S., Sanniti di Baja G., Wang L., Yan W. (eds) Pattern Recognition. ACPR 2019.
Lecture Notes in Computer Science, vol 12046. Springer, Cham. https://doi.org/10.1007/978-3-030-41404-7_23
• [16] https://developers.google.com/machine-learning/gan/
Resources
33
34
Any Questions ?
Thank you
2020-12-16 Creativity based Hardware aware Machine Vision System 35
Parham Zilouchian
p.zilouchian@gmil.com
zilouchian.org
Summary
 GANs are generative models that are implemented using
two stochastic neural network modules: Generator and
Discriminator.
 Generator tries to generate samples from random noise as
input
 Discriminator tries to distinguish the samples from
Generator and samples from the real data distribution.
 Both networks are trained adversarially (in tandem) to
fool the other component. In this process, both models
become better at their respective tasks.
36

More Related Content

What's hot

“From Inference to Action: AI Beyond Pattern Recognition,” a Keynote Presenta...
“From Inference to Action: AI Beyond Pattern Recognition,” a Keynote Presenta...“From Inference to Action: AI Beyond Pattern Recognition,” a Keynote Presenta...
“From Inference to Action: AI Beyond Pattern Recognition,” a Keynote Presenta...
Edge AI and Vision Alliance
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
PyData
 

What's hot (20)

Deep Learning With Python Tutorial | Edureka
Deep Learning With Python Tutorial | EdurekaDeep Learning With Python Tutorial | Edureka
Deep Learning With Python Tutorial | Edureka
 
Why is Deep learning hot right now? and How can we apply it on each day job?
Why is Deep learning hot right now? and How can we apply it on each day job?Why is Deep learning hot right now? and How can we apply it on each day job?
Why is Deep learning hot right now? and How can we apply it on each day job?
 
Deep Learning Projects - Anomaly Detection Using Deep Learning
Deep Learning Projects - Anomaly Detection Using Deep LearningDeep Learning Projects - Anomaly Detection Using Deep Learning
Deep Learning Projects - Anomaly Detection Using Deep Learning
 
Machine Learning vs. Deep Learning
Machine Learning vs. Deep LearningMachine Learning vs. Deep Learning
Machine Learning vs. Deep Learning
 
Machine Learning for Dummies (without mathematics)
Machine Learning for Dummies (without mathematics)Machine Learning for Dummies (without mathematics)
Machine Learning for Dummies (without mathematics)
 
Machine learning seminar ppt
Machine learning seminar pptMachine learning seminar ppt
Machine learning seminar ppt
 
Tutorial on Deep learning and Applications
Tutorial on Deep learning and ApplicationsTutorial on Deep learning and Applications
Tutorial on Deep learning and Applications
 
Introduction to machine learning
Introduction to machine learningIntroduction to machine learning
Introduction to machine learning
 
Computer vision, machine, and deep learning
Computer vision, machine, and deep learningComputer vision, machine, and deep learning
Computer vision, machine, and deep learning
 
“From Inference to Action: AI Beyond Pattern Recognition,” a Keynote Presenta...
“From Inference to Action: AI Beyond Pattern Recognition,” a Keynote Presenta...“From Inference to Action: AI Beyond Pattern Recognition,” a Keynote Presenta...
“From Inference to Action: AI Beyond Pattern Recognition,” a Keynote Presenta...
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
 
International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)
 
Introduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep LearningIntroduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep Learning
 
Deep learning summary
Deep learning summaryDeep learning summary
Deep learning summary
 
Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)
 
Introduction to deep learning workshop
Introduction to deep learning workshopIntroduction to deep learning workshop
Introduction to deep learning workshop
 
Machine model to classify dogs and cat
Machine model to classify dogs and catMachine model to classify dogs and cat
Machine model to classify dogs and cat
 
Machine learning
Machine learningMachine learning
Machine learning
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
An Introduction to Deep Learning
An Introduction to Deep LearningAn Introduction to Deep Learning
An Introduction to Deep Learning
 

Similar to brief Introduction to Different Kinds of GANs

Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
Codiax
 
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...
宏毅 李
 
GAN Deep Learning Approaches to Image Processing Applications (1).pptx
GAN Deep Learning Approaches to Image Processing Applications (1).pptxGAN Deep Learning Approaches to Image Processing Applications (1).pptx
GAN Deep Learning Approaches to Image Processing Applications (1).pptx
RMDAcademicCoordinat
 
contrastive-learning2.pdf
contrastive-learning2.pdfcontrastive-learning2.pdf
contrastive-learning2.pdf
omogire
 

Similar to brief Introduction to Different Kinds of GANs (20)

Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
 
Generative Adversarial Networks and Their Applications in Medical Imaging
Generative Adversarial Networks  and Their Applications in Medical ImagingGenerative Adversarial Networks  and Their Applications in Medical Imaging
Generative Adversarial Networks and Their Applications in Medical Imaging
 
Generative Adversarial Networks GAN - Xavier Giro - UPC TelecomBCN Barcelona ...
Generative Adversarial Networks GAN - Xavier Giro - UPC TelecomBCN Barcelona ...Generative Adversarial Networks GAN - Xavier Giro - UPC TelecomBCN Barcelona ...
Generative Adversarial Networks GAN - Xavier Giro - UPC TelecomBCN Barcelona ...
 
Reading group gan - 20170417
Reading group   gan - 20170417Reading group   gan - 20170417
Reading group gan - 20170417
 
Deep Generative Models - Kevin McGuinness - UPC Barcelona 2018
Deep Generative Models - Kevin McGuinness - UPC Barcelona 2018Deep Generative Models - Kevin McGuinness - UPC Barcelona 2018
Deep Generative Models - Kevin McGuinness - UPC Barcelona 2018
 
gan.pdf
gan.pdfgan.pdf
gan.pdf
 
EuroSciPy 2019 - GANs: Theory and Applications
EuroSciPy 2019 - GANs: Theory and ApplicationsEuroSciPy 2019 - GANs: Theory and Applications
EuroSciPy 2019 - GANs: Theory and Applications
 
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...
 
GAN - Theory and Applications
GAN - Theory and ApplicationsGAN - Theory and Applications
GAN - Theory and Applications
 
Generative Models and Adversarial Training (D2L3 Insight@DCU Machine Learning...
Generative Models and Adversarial Training (D2L3 Insight@DCU Machine Learning...Generative Models and Adversarial Training (D2L3 Insight@DCU Machine Learning...
Generative Models and Adversarial Training (D2L3 Insight@DCU Machine Learning...
 
GAN Deep Learning Approaches to Image Processing Applications (1).pptx
GAN Deep Learning Approaches to Image Processing Applications (1).pptxGAN Deep Learning Approaches to Image Processing Applications (1).pptx
GAN Deep Learning Approaches to Image Processing Applications (1).pptx
 
Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networks
 
Deep image generating models
Deep image generating modelsDeep image generating models
Deep image generating models
 
Deep Generative Modelling
Deep Generative ModellingDeep Generative Modelling
Deep Generative Modelling
 
GDC2019 - SEED - Towards Deep Generative Models in Game Development
GDC2019 - SEED - Towards Deep Generative Models in Game DevelopmentGDC2019 - SEED - Towards Deep Generative Models in Game Development
GDC2019 - SEED - Towards Deep Generative Models in Game Development
 
contrastive-learning2.pdf
contrastive-learning2.pdfcontrastive-learning2.pdf
contrastive-learning2.pdf
 
Project_Final_Review.pdf
Project_Final_Review.pdfProject_Final_Review.pdf
Project_Final_Review.pdf
 
Generative Adversarial Networks and Their Applications
Generative Adversarial Networks and Their ApplicationsGenerative Adversarial Networks and Their Applications
Generative Adversarial Networks and Their Applications
 
Generative Adversarial Network (GAN)
Generative Adversarial Network (GAN)Generative Adversarial Network (GAN)
Generative Adversarial Network (GAN)
 
Generative Adversarial Networks 2
Generative Adversarial Networks 2Generative Adversarial Networks 2
Generative Adversarial Networks 2
 

Recently uploaded

Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
amitlee9823
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
amitlee9823
 
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
amitlee9823
 
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts ServiceCall Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Riyadh +966572737505 get cytotec
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
amitlee9823
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
MarinCaroMartnezBerg
 
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
amitlee9823
 
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
amitlee9823
 
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAl Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
AroojKhan71
 

Recently uploaded (20)

Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
 
(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7
(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7
(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7
 
Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFx
 
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
 
Predicting Loan Approval: A Data Science Project
Predicting Loan Approval: A Data Science ProjectPredicting Loan Approval: A Data Science Project
Predicting Loan Approval: A Data Science Project
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Research
 
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFx
 
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts ServiceCall Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
 
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
 
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
 
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
 
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAl Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
 
Capstone Project on IBM Data Analytics Program
Capstone Project on IBM Data Analytics ProgramCapstone Project on IBM Data Analytics Program
Capstone Project on IBM Data Analytics Program
 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptx
 

brief Introduction to Different Kinds of GANs

  • 2. Outline • Part 1: Introduction to GANs • Part 2: Applications of GANs • Part 3: Project Introduction 2
  • 4. GANs • Generative • Learn a generative model • Adversarial • Trained in an adversarial setting • Networks • Use Deep Neural Networks 4
  • 5. Generative Adversarial Networks (Ian J. Goodfellow, 10 Jun 2014) 5  Two components, the generator and the discriminator:  The generator G needs to capture the data distribution.  The discriminator D estimates the probability that a sample comes from the training data rather than from G.
  • 6. • The discriminator in a GAN is simply a classifier. • It tries to distinguish real data from the data created by the generator. • It could use any network architecture appropriate to the type of data it’s classifying. The Discriminator 1 2 3 6
  • 7. The Generator 7 1. Produce generator output from sampled random noise. 2. Get discriminator "Real" or "Fake" classification for generator output. 3. Calculate loss from discriminator classification. 4. Backpropagate through both the discriminator and generator to obtain gradients. 5. Use gradients to change only the generator weights. 1 2 3 4 5
  • 8. 8 Overview of GAN Structure
  • 10. Why Generative Models?  We’ve only seen discriminative models so far • Given an image X, predict a label Y • Estimates P(Y|X) Discriminative models have several key limitations • Can’t model P(X), i.e. the probability of seeing a certain image • • Thus, can’t sample from P(X), i.e. can’t generate new images Generative models (in general) cope with all of above • Can model P(X) • Can generate new images • We can use these new images for lack of enough data. 10
  • 11. Semi – Supervised GANs (5 Jun 2016, Augustus Odena) 11 • In Normal GANs we train both Generator & Discriminator at the same time. / after training we discard the discriminator because we used it just for training the Generator. • For semi-supervised learning, we need to transform the discriminator into a multi-class classifier. • for each input image, the discriminator has to learn the probabilities of it being a one, two, three and so on. • Help the Generator to produce realistic images ⇒ we have to instruct the Discriminator to distinguish between real / fake samples. • Use the Generator’s Images, along with the labeled & Unlabeled training data, to help classify the dataset. 1 2 3 4 5
  • 12. Semi – Supervised GANs VS. Normal GANs 12 96.4 92.8 88.3 80.2 96.5 89.5 85.9 75 0 10 20 30 40 50 60 70 80 90 100 1000 Sample 100 Sample 50 Sample 25 Sample Model Accuracy # of Samples Compare Accuracy of training with different # of samples SGAN GAN
  • 13. What is DCGAN? (19 Nov 2015 , Alec Radford)  DCGAN: Deep Convolutional Generative Adversarial Networks  It works in the opposite direction of the image classifier (CNN).  CNN transforms an image to a class label (list of probabilities).  DCGAN generates an image from random parameters. 13
  • 14. Training Strategy of DCGAN  We train two models simultaneously.  CNN: Classifying authentic and fake images.  "Authentic" images are provided as training data to CNN.  DCGAN: Trained to generate images classified as authentic by CNN.  By trying to fool CNN, DCGAN learns to generate images similar to the training data. 14
  • 15. Training Loop of DCGAN 15 P(A) : Probability that A is authentic. P(B) : Probability that B is authentic. By repeating this loop, CNN becomes more accurate and DCGAN becomes more crafty.
  • 17. Latent vectors capture interesting patterns… 17 Radford, Alec, Luke Metz, and Soumith Chintala. "Unsupervised representation learning with deep convolutional generative adversarial networks." arXiv:1511.06434 (2015).
  • 18. STAR GAN (24 Nov 2017, Yunjey Choi) 18
  • 20. FT GAN (19 July 2019, Weiwei Zhuang) 20
  • 23. Character GAN 23  Character GAN: a generative model that can be trained on only a few samples (8 – 15) of a given character.  We train a generative model in a low-data setting (8 to 15 training samples) to repose & animate characters based on keypoint positions.  This model generates novel poses based on keypoint locations.
  • 24. Character GAN 24 • Since we only have limited training samples, one of the key challenges lies in how to address (dis)occlusion. e.g. when a hand moves behind or in front of a body. • To address mentioned problem we introduce a novel layering approach which explicitly splits the input keypoints into different layers which are processed independently. • These layers represent different parts of the character and provide a strong implicit bias that helps to obtain realistic results even with strong (dis)occlusions. • To combine the features of individual layers ⇒ we use an adaptive scaling approach conditioned on all keypoints. • This model scales to larger datasets when more data is available. 1 2 3 4 5
  • 25. Character GAN 25 • (Problem) If some body parts are occluded by others they still exist even though they may not be visible. ⇒ we split our characters into different layers (Solve). • To model different layers, the generator processes each keypoint individually and learns a representation of each keypoint layer. • Adaptive scaling technique: ⇒ we scale the features of each layer before concatenating them! • For AST we first learn an embedding of the keypoints & their layers. ⇔ Based on this embedding we then learn scaling parameters for each keypoint layer & use them to scale the features of each layer. 1 2 3 4 5 • Model: Generator: ⇒ generates the image based on the keypoint location. Discriminator: ⇒ trained to distinguish between real & fake image-keypoint pairs.
  • 26. Character GAN - Layering 1 2 3 4 • our layered approach is beneficial when several keypoints overlap in the 2D space, • e.g. representing the “left” side of the character (e.g. left arm and leg), the “middle” part of the character (e.g. head and torso) and the “right” side of the character (e.g. right arm and leg). • These layers can be modeled individually and can then be composed to form a final image. • To model this, our generator processes each keypoint layer individually and learns a representation of each keypoint layer. 26
  • 27. Character GAN – Patch Based Refinement 1 2 3 4 • To further improve the final result we apply a patch-based refinement algorithm that replaces generated patches with their closest real patch. • In our case, given a real & a generated image, for each patch in the generated image, we find the closest patch in the dataset. • We use Patch Match approximation nearest neighbor algorithm: ⇒ Replace the generated patches with their real equivalent. • This approach often improves the sharpness and general image quality over the output of the generator. 27
  • 30. Construct a combination of Gan Models introduced. Optimize it for Low-Complexity Create a creativity based GAN application Lunch it as an Experimental product Steps Ahead 30
  • 32. • [1] Goodfellow, I., et al.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) NIPS 2014, pp. 2672–2680 (2014) • [2] Bengio, Y. (2009). Learning deep architectures for AI. Now Publishers. • [3] Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: ICLR 2016 (2016) • [4] Hinton, G., Deng, L., Dahl, G. E., Mohamed, A., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., and Kingsbury, B. (2012a). Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Processing Magazine, 29(6), 82–97. • [5] Krizhevsky, A., Sutskever, I., and Hinton, G. (2012). ImageNet classification with deep convolutional neural networks. In NIPS’2012. • [6] Jarrett, K., Kavukcuoglu, K., Ranzato, M., and LeCun, Y. (2009). What is the best multi-stage architecture for object recognition? In Proc. International Conference on Computer Vision (ICCV’09), pages 2146–2153. IEEE. • [7] Goodfellow, I. J., Mirza, M., Courville, A., and Bengio, Y. (2013b). Multi-prediction deep Boltzmann machines. In NIPS’2013. • [8] Hinz, T., Fisher, M., Wang, O., Shechtman, E., and Wermter, S., “CharacterGAN: Few-Shot Keypoint Character Animation and Reposing”, 2021. Link: https://arxiv.org/abs/2102.03141 Resources 32
  • 33. • [9] Choi, H., Park, C. and Lee, K., 2020. From Inference To Generation: End-To-End Fully Self-Supervised Generation Of Human Face From Speech. • [10] Odena, Augustus. “Semi-Supervised Learning with Generative Adversarial Networks.” ArXiv abs/1606.01583 (2016): n. pag. • [11] Chen, Xiang et al. “FTGAN: A Fully-trained Generative Adversarial Networks for Text to Face Generation.” ArXiv abs/1904.05729 (2019): n. pag. • [12] Y. Choi, M. Choi, M. Kim, J. Ha, S. Kim and J. Choo, "StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, 2018, pp. 8789-8797, doi: 10.1109/CVPR.2018.00916. • [13] K. Kumar, R. Kumar, T. de Boissiere, L. Gestin, W. Z. Teoh, J. Sotelo, A. de Brebisson, Y. Bengio, and A. Courville, “MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis,” arXiv.org, 09-Dec-2019. • [14] S. Palazzo, C. Spampinato, I. Kavasidis, D. Giordano and M. Shah, "Generative Adversarial Networks Conditioned by Brain Signals," in 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy • [15] Shimizu T., Xu J., Tasaka K. (2020) MobileGAN: Compact Network Architecture for Generative Adversarial Network. In: Palaiahnakote S., Sanniti di Baja G., Wang L., Yan W. (eds) Pattern Recognition. ACPR 2019. Lecture Notes in Computer Science, vol 12046. Springer, Cham. https://doi.org/10.1007/978-3-030-41404-7_23 • [16] https://developers.google.com/machine-learning/gan/ Resources 33
  • 35. Thank you 2020-12-16 Creativity based Hardware aware Machine Vision System 35 Parham Zilouchian p.zilouchian@gmil.com zilouchian.org
  • 36. Summary  GANs are generative models that are implemented using two stochastic neural network modules: Generator and Discriminator.  Generator tries to generate samples from random noise as input  Discriminator tries to distinguish the samples from Generator and samples from the real data distribution.  Both networks are trained adversarially (in tandem) to fool the other component. In this process, both models become better at their respective tasks. 36