Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation

Yan Jin, Mengke Li, Yang Lu*, Yiu-ming Cheung, Hanzi Wang

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

Deep neural networks have made huge progress in the last few decades. However, as the real-world data often exhibits a long-tailed distribution, vanilla deep models tend to be heavily biased toward the majority classes. To address this problem, state-of-the-art methods usually adopt a mixture of experts (MoE) to focus on different parts of the long-tailed distribution. Experts in these methods are with the same model depth, which neglects the fact that different classes may have different preferences to be fit by models with different depths. To this end, we propose a novel MoE-based method called Self-Heterogeneous Integration with Knowledge Excavation (SHIKE). We first propose Depth-wise Knowledge Fusion (DKF) to fuse features between different shallow parts and the deep part in one network for each expert, which makes experts more diverse in terms of representation. Based on DKF, we further propose Dynamic Knowledge Transfer (DKT) to reduce the influence of the hardest negative class that has a non-negligible impact on the tail classes in our MoE framework. As a result, the classification accuracy of long-tailed data can be significantly improved, especially for the tail classes. SHIKE achieves the state-of-the-art performance of 56.3%, 60.3%, 75.4%, and 41.9% on CIFAR100-LT (IF100), ImageNet-LT, iNaturalist 2018, and Places-LT, respectively. The source code is available at https://github.com/jinyan-06/SHIKE.
Original languageEnglish
Title of host publicationProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
Place of PublicationVancouver, BC, Canada
PublisherIEEE
Pages23695-23704
Number of pages10
ISBN (Electronic)9798350301298
ISBN (Print)9798350301304
DOIs
Publication statusPublished - 18 Jun 2023
Event36th IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 - Vancouver, Canada
Duration: 17 Jun 202322 Jun 2023
https://cvpr2023.thecvf.com/
https://openaccess.thecvf.com/CVPR2023
https://ieeexplore.ieee.org/xpl/conhome/10203037/proceeding

Publication series

NameConference on Computer Vision and Pattern Recognition (CVPR)
ISSN (Print)1063-6919
ISSN (Electronic)2575-7075

Conference

Conference36th IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
Country/TerritoryCanada
CityVancouver
Period17/06/2322/06/23
Internet address

Fingerprint

Dive into the research topics of 'Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation'. Together they form a unique fingerprint.

Cite this