Joint Learning of Generative Translator and Classifier for Visually Similar Classes

In this paper, we propose a Generative Translation Classification Network (GTCN) for improving visual classification accuracy in settings where classes are visually similar and data is scarce. For this purpose, we propose joint learning from a scratch to train a classifier and a generative stochastic translation network end-to-end. The translation network is used to perform on-line data augmentation across classes, whereas previous works have mostly involved domain adaptation. To help the model further benefit from this data-augmentation, we introduce an adaptive fade-in loss and a quadruplet loss. We perform experiments on multiple datasets to demonstrate the proposed method’s performance in varied settings. Of particular interest, training on 40% of the dataset is enough for our model to surpass the performance of baselines trained on the full dataset. When our architecture is trained on the full dataset, we achieve comparable performance with state-of-the-art methods despite using a light-weight architecture.

[1]  Xiaoming Liu,et al.  Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[2]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[3]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Addisson Salazar,et al.  Surrogate techniques for testing fraud detection algorithms in credit card operations , 2014, 2014 International Carnahan Conference on Security Technology (ICCST).

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

[6]  Tatsuya Harada,et al.  Between-Class Learning for Image Classification , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Abdenour Hadid,et al.  An original face anti-spoofing approach using partial convolutional neural network , 2016, 2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA).

[8]  Fan Yang,et al.  Good Semi-supervised Learning That Requires a Bad GAN , 2017, NIPS.

[9]  Tien Dat Nguyen,et al.  Combining Deep and Handcrafted Image Features for Presentation Attack Detection in Face Recognition Systems Using Visible-Light Camera Sensors , 2018, Sensors.

[10]  Jan Kautz,et al.  Multimodal Unsupervised Image-to-Image Translation , 2018, ECCV.

[11]  Tom White,et al.  Generative Adversarial Networks: An Overview , 2017, IEEE Signal Processing Magazine.

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

[13]  Lior Wolf,et al.  Unsupervised Cross-Domain Image Generation , 2016, ICLR.

[14]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[15]  Shiqi Wang,et al.  Learning Generalized Deep Feature Representation for Face Anti-Spoofing , 2018, IEEE Transactions on Information Forensics and Security.

[16]  R. Devon Hjelm,et al.  Locality and compositionality in zero-shot learning , 2019, ICLR.

[17]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[18]  Xiaoming Liu,et al.  Face anti-spoofing using patch and depth-based CNNs , 2017, 2017 IEEE International Joint Conference on Biometrics (IJCB).

[19]  Stan Z. Li,et al.  Learn Convolutional Neural Network for Face Anti-Spoofing , 2014, ArXiv.

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

[21]  Xu Zhao,et al.  Face spoofing detection by fusing binocular depth and spatial pyramid coding micro-texture features , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[22]  Guifen Tian,et al.  Spoofing detection for embedded face recognition system using a low cost stereo camera , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

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

[24]  Di Tang,et al.  Face Flashing: a Secure Liveness Detection Protocol based on Light Reflections , 2018, NDSS.

[25]  Aaron C. Courville,et al.  Adversarially Learned Inference , 2016, ICLR.

[26]  Jan Kautz,et al.  Unsupervised Image-to-Image Translation Networks , 2017, NIPS.

[27]  Philip Bachman,et al.  Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data , 2018, ICML.

[28]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[29]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[30]  Zhe Gan,et al.  Triangle Generative Adversarial Networks , 2017, NIPS.

[31]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[33]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

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

[35]  R. Fisher THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[36]  Maneesh Kumar Singh,et al.  DRIT++: Diverse Image-to-Image Translation via Disentangled Representations , 2019, International Journal of Computer Vision.

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

[38]  Alexei A. Efros,et al.  Toward Multimodal Image-to-Image Translation , 2017, NIPS.

[39]  Jung-Woo Ha,et al.  StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[40]  Junjie Yan,et al.  A face antispoofing database with diverse attacks , 2012, 2012 5th IAPR International Conference on Biometrics (ICB).

[41]  H. Eichenbaum,et al.  Interplay of Hippocampus and Prefrontal Cortex in Memory , 2013, Current Biology.

[42]  Amos J. Storkey,et al.  Data Augmentation Generative Adversarial Networks , 2017, ICLR 2018.

[43]  Kaiqi Huang,et al.  Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[44]  Yaman Akbulut,et al.  Deep learning based face liveness detection in videos , 2017, 2017 International Artificial Intelligence and Data Processing Symposium (IDAP).