Deep Long-Tailed Learning: A Survey

Abstract

Deep long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing deep models from a large number of images that follow a long-tailed class distribution. In the last decade, deep learning has emerged as a powerful recognition model for learning high-quality image representations and has led to remarkable breakthroughs in generic visual recognition. However, long-tailed class imbalance, a common problem in practical visual recognition tasks, often limits the practicality of deep network based recognition models in real-world applications, since they can be easily biased towards dominant classes and perform poorly on tail classes. To address this problem, a large number of studies have been conducted in recent years, making promising progress in the field of deep long-tailed learning. Considering the rapid evolution of this field, this paper aims to provide a comprehensive survey on recent advances in deep long-tailed learning. To be specific, we group existing deep long-tailed learning studies into three main categories (i.e., class re-balancing, information augmentation and module improvement), and review these methods following this taxonomy in detail. Afterward, we empirically analyze several state-of-the-art methods by evaluating to what extent they address the issue of class imbalance via a newly proposed evaluation metric, i.e., relative accuracy. We conclude the survey by highlighting important applications of deep long-tailed learning and identifying several promising directions for future research.

Published in IEEE Transactions on Pattern Analysis and Machine Intelligence

References in corpus (14)

• Distilling the Knowledge in a Neural Network
• The Effectiveness of Data Augmentation in Image Classification using Deep Learning
• Towards Out-Of-Distribution Generalization: A Survey
• Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
• One Million Scenes for Autonomous Driving: ONCE Dataset
• COVID-DA: Deep Domain Adaptation from Typical Pneumonia to COVID-19
• Striking the Right Balance with Uncertainty
• Vocabulary-informed Zero-shot and Open-set Learning
• Robust Long-Tailed Learning under Label Noise
• Learning From Long-Tailed Data With Noisy Labels
• Compositional Prototype Network with Multi-view Comparision for Few-Shot Point Cloud Semantic Segmentation
• An Effective and Robust Detector for Logo Detection
• Fine-Grained Visual Classification of Plant Species In The Wild: Object Detection as A Reinforced Means of Attention
• AdaXpert: Adapting Neural Architecture for Growing Data

Cited by in corpus (5)

• Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment
• When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework and A New Benchmark
• Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning
• Targeted Supervised Contrastive Learning for Long-Tailed Recognition
• FAR-AMTN: Attention Multi-Task Network for Face Attribute Recognition