A Three-Player GAN: Generating Hard Samples to Improve Classification Networks

We propose a Three-Player Generative Adversarial Network to improve classification networks. In addition to the game played between the discriminator and generator, a competition is introduced between the generator and the classifier. The generator's objective is to synthesize samples that are both realistic and hard to label for the classifier. Even though we make no assumptions on the type of augmentations to learn, we find that the model is able to synthesize realistically looking examples that are hard for the classification model. Furthermore, the classifier becomes more robust when trained on these difficult samples. The method is evaluated on a public dataset for traffic sign recognition.

[1]  Ghassan Al-Regib,et al.  CURE-TSR: Challenging Unreal and Real Environments for Traffic Sign Recognition , 2017, ArXiv.

[2]  Augustus Odena,et al.  Semi-Supervised Learning with Generative Adversarial Networks , 2016, ArXiv.

[3]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[4]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[5]  Han Zhang,et al.  Self-Attention Generative Adversarial Networks , 2018, ICML.

[6]  Jeff Donahue,et al.  Large Scale GAN Training for High Fidelity Natural Image Synthesis , 2018, ICLR.

[7]  Jost Tobias Springenberg,et al.  Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks , 2015, ICLR.

[8]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[10]  Takeru Miyato,et al.  cGANs with Projection Discriminator , 2018, ICLR.

[11]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[12]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[13]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[14]  Jun Zhu,et al.  Triple Generative Adversarial Nets , 2017, NIPS.

[15]  Fei Yang,et al.  Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[16]  Victor S. Lempitsky,et al.  Unsupervised Domain Adaptation by Backpropagation , 2014, ICML.