Tackling long-tailed category distribution under domain shifts
File(s)
Accepted version
Author(s)
Type
Conference Paper
Abstract
Machine learning models fail to perform well on real-world applications when 1) the category distribution P(Y) of the training dataset suffers from long-tailed distribution and 2) the test data is drawn from different conditional distributions P(X|Y). Existing approaches cannot handle the scenario where both issues exist, which however is common for real-world applications. In this study, we took a step forward and looked into the problem of long-tailed classification under domain shifts. We designed three novel core functional blocks including Distribution Calibrated Classification Loss, Visual-Semantic Mapping and Semantic-Similarity Guided Augmentation. Furthermore, we adopted a meta-learning framework which integrates these three blocks to improve domain generalization on unseen target domains. Two new datasets were proposed for this problem, named AWA2-LTS and ImageNet-LTS. We evaluated our method on the two datasets and extensive experimental results demonstrate that our proposed method can achieve superior performance over state-of-the-art long-tailed/domain generalization approaches and the combinations. Source codes and datasets can be found at our project page https://xiaogu.site/LTDS.
Date Issued
2022-10-28
Date Acceptance
2022-07-03
Citation
Lecture Notes in Computer Science, 2022, pp.727-743
ISSN
0302-9743
Publisher
Springer
Start Page
727
End Page
743
Journal / Book Title
Lecture Notes in Computer Science
Copyright Statement
Copyright © 2022 Springer-Verlag. This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-031-20050-2_42
Identifier
https://link.springer.com/chapter/10.1007/978-3-031-20050-2_42
Source
European Conference on Computer Vision (ECCV 2022)
Publication Status
Accepted
Start Date
2022-10-23
Finish Date
2022-10-27
Coverage Spatial
Tel-Aviv, Israel
Date Publish Online
2022-10-28