RSG: A Simple but Effective Module for Learning Imbalanced Datasets

TL;DR

This paper introduces RSG, a versatile data augmentation module that generates samples for rare classes during training, significantly improving deep neural network performance on imbalanced datasets without affecting testing efficiency.

Contribution

The paper proposes RSG, a simple and effective module for generating rare class samples during training, compatible with various networks and loss functions, achieving state-of-the-art results.

Findings

RSG improves performance on imbalanced datasets.

RSG achieves new state-of-the-art on Places-LT, ImageNet-LT, and iNaturalist 2018.

RSG is easy to integrate and does not increase testing burden.

Abstract

Imbalanced datasets widely exist in practice and area great challenge for training deep neural models with agood generalization on infrequent classes. In this work, wepropose a new rare-class sample generator (RSG) to solvethis problem. RSG aims to generate some new samplesfor rare classes during training, and it has in particularthe following advantages: (1) it is convenient to use andhighly versatile, because it can be easily integrated intoany kind of convolutional neural network, and it works wellwhen combined with different loss functions, and (2) it isonly used during the training phase, and therefore, no ad-ditional burden is imposed on deep neural networks duringthe testing phase. In extensive experimental evaluations, weverify the effectiveness of RSG. Furthermore, by leveragingRSG, we obtain competitive results on Imbalanced CIFARand new state-of-the-art results on Places-LT, ImageNet-LT, and iNaturalist 2018. The source code is available at https://github.com/Jianf-Wang/RSG.