Log In Sign Up

Mitigating Dataset Imbalance via Joint Generation and Classification

by   Aadarsh Sahoo, et al.

Supervised deep learning methods are enjoying enormous success in many practical applications of computer vision and have the potential to revolutionize robotics. However, the marked performance degradation to biases and imbalanced data questions the reliability of these methods. In this work we address these questions from the perspective of dataset imbalance resulting out of severe under-representation of annotated training data for certain classes and its effect on both deep classification and generation methods. We introduce a joint dataset repairment strategy by combining a neural network classifier with Generative Adversarial Networks (GAN) that makes up for the deficit of training examples from the under-representated class by producing additional training examples. We show that the combined training helps to improve the robustness of both the classifier and the GAN against severe class imbalance. We show the effectiveness of our proposed approach on three very different datasets with different degrees of imbalance in them. The code is available at .


page 13

page 25

page 26

page 27

page 28

page 29

page 30


Deep Learning for Imbalance Data Classification using Class Expert Generative Adversarial Network

Without any specific way for imbalance data classification, artificial i...

CIGAN: A Python Package for Handling Class Imbalance using Generative Adversarial Networks

A key challenge in Machine Learning is class imbalance, where the sample...

How to train your draGAN: A task oriented solution to imbalanced classification

The long-standing challenge of building effective classification models ...

WhyGen: Explaining ML-powered Code Generation by Referring to Training Examples

Deep learning has demonstrated great abilities in various code generatio...

Posterior Re-calibration for Imbalanced Datasets

Neural Networks can perform poorly when the training label distribution ...

RealPatch: A Statistical Matching Framework for Model Patching with Real Samples

Machine learning classifiers are typically trained to minimise the avera...

Scaling Up Influence Functions

We address efficient calculation of influence functions for tracking pre...

Code Repositories


This repository contains code for the paper "Mitigating Dataset Imbalance via Joint Generation and Classification", published at ECCV-2020 Workshop on Imbalance Problems in Computer Vision (IPCV).

view repo