Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective

Muhammad Abdullah Jamal, Matthew Brown, Ming Hsuan Yang, Liqiang Wang, Boqing Gong

Research output: Contribution to journalConference articlepeer-review

183 Citations (Scopus)


Object frequency in the real world often follows a power law, leading to a mismatch between datasets with long-tailed class distributions seen by a machine learning model and our expectation of the model to perform well on all classes. We analyze this mismatch from a domain adaptation point of view. First of all, we connect existing class-balanced methods for long-tailed classification to target shift, a well-studied scenario in domain adaptation. The connection reveals that these methods implicitly assume that the training data and test data share the same class-conditioned distribution, which does not hold in general and especially for the tail classes. While a head class could contain abundant and diverse training examples that well represent the expected data at inference time, the tail classes are often short of representative training data. To this end, we propose to augment the classic class-balanced learning by explicitly estimating the differences between the class-conditioned distributions with a meta-learning approach. We validate our approach with six benchmark datasets and three loss functions.

Original languageEnglish
Article number9157687
Pages (from-to)7607-7616
Number of pages10
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publication statusPublished - 2020
Event2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 - Virtual, Online, United States
Duration: 2020 Jun 142020 Jun 19

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective'. Together they form a unique fingerprint.

Cite this