TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Long-tail Learning	CIFAR-100-LT (ρ=10)	LCReg	Error Rate	35.8	# 15
Long-tail Learning	CIFAR-10-LT (ρ=10)	LCReg	Error Rate	8.8	# 9

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/long-tailed-recognition-by-learning-from-1/long-tail-learning-on-cifar-10-lt-r-10)](https://paperswithcode.com/sota/long-tail-learning-on-cifar-10-lt-r-10?p=long-tailed-recognition-by-learning-from-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/long-tailed-recognition-by-learning-from-1/long-tail-learning-on-cifar-100-lt-r-10)](https://paperswithcode.com/sota/long-tail-learning-on-cifar-100-lt-r-10?p=long-tailed-recognition-by-learning-from-1)`

Long-tailed Recognition by Learning from Latent Categories

2 Jun 2022 · Weide Liu, Zhonghua Wu, Yiming Wang, Henghui Ding, Fayao Liu, Jie Lin, Guosheng Lin ·

In this work, we address the challenging task of long-tailed image recognition. Previous long-tailed recognition methods commonly focus on the data augmentation or re-balancing strategy of the tail classes to give more attention to tail classes during the model training. However, due to the limited training images for tail classes, the diversity of tail class images is still restricted, which results in poor feature representations. In this work, we hypothesize that common latent features among the head and tail classes can be used to give better feature representation. Motivated by this, we introduce a Latent Categories based long-tail Recognition (LCReg) method. Specifically, we propose to learn a set of class-agnostic latent features shared among the head and tail classes. Then, we implicitly enrich the training sample diversity via applying semantic data augmentation to the latent features. Extensive experiments on five long-tailed image recognition datasets demonstrate that our proposed LCReg is able to significantly outperform previous methods and achieve state-of-the-art results.

PDF Abstract