2021/06/18 by Jianfeng Wang, Thomas Lukasiewicz, Wang, Jianfeng +7 · 3 citations
Computer Science · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Imbalanced Data Classification Techniques #cs.CV
paper · pdf · doi:10.48550/arxiv.2106.09859
To appear at CVPR 2021. We propose a flexible data generation/data augmentation module for long-tailed classification. Codes are available at: https://github.com/Jianf-Wang/RSG
arxiv created 2021/06/18 · openalex publication_date 2021/06/18 · arxiv updated 2021/06/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.