Mitigating Dataset Imbalance via
Joint Generation and Classification
Aadarsh Sahoo1
Ankit Singh2
Rameswar Panda3
Rogerio Feris3
Abir Das1
1 IIT Kharagpur
2 IIT Madras
3 MIT-IBM Watson AI Lab
IPCV Workshop at ECCV 2020


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.

Experimental Results Overview

Paper & Code

Aadarsh Sahoo, Ankit Singh, Rameswar Panda, Rogerio Feris, Abir Das
Mitigating Dataset Imbalance via Joint Generation and Classification
ECCV2020 Workshop on Imbalance Problems in Computer Vision (ECCV-W), 2020
[PDF] [Supp] [Poster] [Slides] [Code]