DeepAI AI Chat
Log In Sign Up

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

by   Florent Chiaroni, et al.

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.


page 9

page 14

page 16

page 17


Learning From Positive and Unlabeled Data Using Observer-GAN

The problem of learning from positive and unlabeled data (A.K.A. PU lear...

How Does GAN-based Semi-supervised Learning Work?

Generative adversarial networks (GANs) have been widely used and have ac...

On Positive-Unlabeled Classification in GAN

This paper defines a positive and unlabeled classification problem for s...

GAN-based Recommendation with Positive-Unlabeled Sampling

Recommender systems are popular tools for information retrieval tasks on...

Training Generative Adversarial Networks from Incomplete Observations using Factorised Discriminators

Generative adversarial networks (GANs) have shown great success in appli...

RankGAN: A Maximum Margin Ranking GAN for Generating Faces

We present a new stage-wise learning paradigm for training generative ad...