TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Long-tail Learning	ImageNet-LT	Logit adjustment	Top-1 Accuracy	51.3	# 49

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/long-tail-learning-via-logit-adjustment/long-tail-learning-on-imagenet-lt)](https://paperswithcode.com/sota/long-tail-learning-on-imagenet-lt?p=long-tail-learning-via-logit-adjustment)`

Long-tail learning via logit adjustment

ICLR 2021 · Aditya Krishna Menon, Sadeep Jayasumana, Ankit Singh Rawat, Himanshu Jain, Andreas Veit, Sanjiv Kumar ·

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.