English

Long-tail learning via logit adjustment

Machine Learning 2021-07-13 v2 Machine Learning

Abstract

Real-world classification problems typically exhibit an imbalanced or long-tailed label distribution, wherein many labels are associated with only a few samples. This poses a challenge for generalisation on such labels, and also makes na\"ive learning biased towards dominant labels. In this paper, we present two simple modifications of standard softmax cross-entropy training to cope with these challenges. Our techniques revisit the classic idea of logit adjustment based on the label frequencies, either applied post-hoc to a trained model, or enforced in the loss during training. Such adjustment encourages a large relative margin between logits of rare versus dominant labels. These techniques unify and generalise several recent proposals in the literature, while possessing firmer statistical grounding and empirical performance.

Keywords

Cite

@article{arxiv.2007.07314,
  title  = {Long-tail learning via logit adjustment},
  author = {Aditya Krishna Menon and Sadeep Jayasumana and Ankit Singh Rawat and Himanshu Jain and Andreas Veit and Sanjiv Kumar},
  journal= {arXiv preprint arXiv:2007.07314},
  year   = {2021}
}

Comments

Published as a conference paper in ICLR 2021

R2 v1 2026-06-23T17:07:21.783Z