A Systematic Review on Long-Tailed Learning

TL;DR

This paper provides a comprehensive survey of recent advances in long-tailed visual learning, introducing a new taxonomy and analyzing various methods to improve performance on imbalanced datasets.

Contribution

It proposes a new taxonomy for long-tailed learning, systematically reviews recent methods, and discusses future research directions in the field.

Findings

Identifies eight key dimensions of long-tailed learning methods.

Highlights differences between imbalance learning and long-tailed learning.

Provides insights into future challenges and opportunities.

Abstract

Long-tailed data is a special type of multi-class imbalanced data with a very large amount of minority/tail classes that have a very significant combined influence. Long-tailed learning aims to build high-performance models on datasets with long-tailed distributions, which can identify all the classes with high accuracy, in particular the minority/tail classes. It is a cutting-edge research direction that has attracted a remarkable amount of research effort in the past few years. In this paper, we present a comprehensive survey of latest advances in long-tailed visual learning. We first propose a new taxonomy for long-tailed learning, which consists of eight different dimensions, including data balancing, neural architecture, feature enrichment, logits adjustment, loss function, bells and whistles, network optimization, and post hoc processing techniques. Based on our proposed taxonomy, we present a systematic review of long-tailed learning methods, discussing their commonalities and alignable differences. We also analyze the differences between imbalance learning and long-tailed learning approaches. Finally, we discuss prospects and future directions in this field.