Learning with A Generative Adversarial Network From a Positive Unlabeled Dataset for Image Classification

In this paper, we propose a new approach which addresses the Positive Unlabeled learning challenge for image classification. Its functioning is based on GAN abilities in order to generate fake images samples whose distribution gets closer to negative samples distribution included in the unlabeled dataset available, while being different to the distribution of the unlabeled positive samples. Then we train a CNN classifier with the positive samples and the fake generated samples, as it would be done with a classic Positive Negative dataset. The tests performed on three different image classification datasets show that the system is stable up to an acceptable fraction of positive samples present in the unlabeled dataset. Although very different, this method outperforms the state of the art PU learning on the RGB dataset CIFAR-10.

[1]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[2]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[3]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[4]  Tailin Wu,et al.  Learning with Confident Examples: Rank Pruning for Robust Classification with Noisy Labels , 2017, UAI.

[5]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Brahim Chaib-draa,et al.  A generative adversarial framework for positive-unlabeled classification , 2017, ArXiv.

[7]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[9]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[10]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  David A. Clifton,et al.  A review of novelty detection , 2014, Signal Process..

[12]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Gang Niu,et al.  Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning , 2016, NIPS.

[14]  David Berthelot,et al.  BEGAN: Boundary Equilibrium Generative Adversarial Networks , 2017, ArXiv.

[15]  Shehroz S. Khan,et al.  One-class classification: taxonomy of study and review of techniques , 2013, The Knowledge Engineering Review.

[16]  David Lopez-Paz,et al.  Optimizing the Latent Space of Generative Networks , 2017, ICML.

[17]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

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

[19]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.