RSG: A Simple but Effective Module for Learning Imbalanced Datasets

Imbalanced datasets widely exist in practice and are a great challenge for training deep neural models with a good generalization on infrequent classes. In this work, we propose a new rare-class sample generator (RSG) to solve this problem. RSG aims to generate some new samples for rare classes duri...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 3783 - 3792
Main Authors: Wang, Jianfeng, Lukasiewicz, Thomas, Hu, Xiaolin, Cai, Jianfei, Xu, Zhenghua
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2021
Subjects:
Codes
Computer vision
Convolutional neural networks
Deep learning
Generators
Pattern recognition
Training
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Imbalanced datasets widely exist in practice and are a great challenge for training deep neural models with a good generalization on infrequent classes. In this work, we propose a new rare-class sample generator (RSG) to solve this problem. RSG aims to generate some new samples for rare classes during training, and it has in particular the following advantages: (1) it is convenient to use and highly versatile, because it can be easily integrated into any kind of convolutional neural network, and it works well when combined with different loss functions, and (2) it is only used during the training phase, and therefore, no additional burden is imposed on deep neural networks during the testing phase. In extensive experimental evaluations, we verify the effectiveness of RSG. Furthermore, by leveraging RSG, we obtain competitive results on Imbalanced CIFAR and 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.
ISSN:1063-6919
DOI:10.1109/CVPR46437.2021.00378