Removing Class Imbalance using Polarity-GAN: An Uncertainty Sampling Approach

12/09/2020
by   Kumari Deepshikha, et al.
0

Class imbalance is a challenging issue in practical classification problems for deep learning models as well as for traditional models. Traditionally successful countermeasures such as synthetic over-sampling have had limited success with complex, structured data handled by deep learning models. In this work, we propose to use a Generative Adversarial Network (GAN) equipped with a generator network G, a discriminator network D and a classifier network C to remove the class-imbalance in visual data sets. The generator network is initialized with auto-encoder to make it stable. The discriminator D ensures that G adheres to class distribution of imbalanced class. In conventional methods, where Generator G competes with discriminator D in a min-max game, we propose to further add an additional classifier network to the original network. Now, the generator network tries to compete in a min-max game with Discriminator as well as the new classifier that we have introduced. An additional condition is enforced on generator network G to produce points in the convex hull of desired imbalanced class. Further the contention of adversarial game with classifier C, pushes conditional distribution learned by G towards the periphery of the respective class, compensating the problem of class imbalance. Experimental evidence shows that this initialization results in stable training of the network. We achieve state of the art performance on extreme visual classification task on the FashionMNIST, MNIST, SVHN, ExDark, MVTec Anomaly Detection dataset, Chest X-Ray dataset and others.

READ FULL TEXT

page 6

page 7

research
03/22/2019

Generative Adversarial Minority Oversampling

Class imbalance is a long-standing problem relevant to a number of real-...
research
10/24/2020

Discriminative feature generation for classification of imbalanced data

The data imbalance problem is a frequent bottleneck in the classificatio...
research
04/25/2017

Deep Over-sampling Framework for Classifying Imbalanced Data

Class imbalance is a challenging issue in practical classification probl...
research
03/08/2019

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

We propose a Three-Player Generative Adversarial Network to improve clas...
research
08/12/2020

Mitigating Dataset Imbalance via Joint Generation and Classification

Supervised deep learning methods are enjoying enormous success in many p...
research
08/20/2021

Does Adversarial Oversampling Help us?

Traditional oversampling methods are generally employed to handle class ...
research
01/22/2019

A New CGAN Technique for Constrained Topology Design Optimization

This paper presents a new conditional GAN (named convex relaxing CGAN or...

Please sign up or login with your details

Forgot password? Click here to reset