Generating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification

Abstract

With surge of available but unlabeled data, Positive Unlabeled (PU) learning is becoming a thriving challenge. This work deals with this demanding task for which recent GAN-based PU approaches have demonstrated promising results. Generative adversarial Networks (GANs) are not hampered by deterministic bias or need for specific dimensionality. However, existing GAN-based PU approaches also present some drawbacks such as sensitive dependence to prior knowledge, a cumbersome architecture or first-stage overfitting. To settle these issues, we propose to incorporate a biased PU risk within the standard GAN discriminator loss function. In this manner, the discriminator is constrained to request the generator to converge towards the unlabeled samples distribution while diverging from the positive samples distribution. This enables the proposed model, referred to as D-GAN, to exclusively learn the counter-examples distribution without prior knowledge. Experiments demonstrate that our approach outperforms state-of-the-art PU methods without prior by overcoming their issues.

arXiv commentSubmitted to Pattern Recognition

References in corpus (10)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities
• Estimating the class prior and posterior from noisy positives and unlabeled data
• Efficient Training for Positive Unlabeled Learning
• Generalizable Adversarial Training via Spectral Normalization
• Learning with Confident Examples: Rank Pruning for Robust Classification with Noisy Labels
• Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators