A Survey on Long-Tailed Visual Recognition

Abstract

The heavy reliance on data is one of the major reasons that currently limit the development of deep learning. Data quality directly dominates the effect of deep learning models, and the long-tailed distribution is one of the factors affecting data quality. The long-tailed phenomenon is prevalent due to the prevalence of power law in nature. In this case, the performance of deep learning models is often dominated by the head classes while the learning of the tail classes is severely underdeveloped. In order to learn adequately for all classes, many researchers have studied and preliminarily addressed the long-tailed problem. In this survey, we focus on the problems caused by long-tailed data distribution, sort out the representative long-tailed visual recognition datasets and summarize some mainstream long-tailed studies. Specifically, we summarize these studies into ten categories from the perspective of representation learning, and outline the highlights and limitations of each category. Besides, we have studied four quantitative metrics for evaluating the imbalance, and suggest using the Gini coefficient to evaluate the long-tailedness of a dataset. Based on the Gini coefficient, we quantitatively study 20 widely-used and large-scale visual datasets proposed in the last decade, and find that the long-tailed phenomenon is widespread and has not been fully studied. Finally, we provide several future directions for the development of long-tailed learning to provide more ideas for readers.

arXiv commentAccepted for publication in International Journal of Computer Vision (IJCV)

References in corpus (21)

• SMOTE: Synthetic Minority Over-sampling Technique
• SSD: Single Shot MultiBox Detector
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• A Simple Framework for Contrastive Learning of Visual Representations
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• A systematic study of the class imbalance problem in convolutional neural networks
• XLNet: Generalized Autoregressive Pretraining for Language Understanding
• YFCC100M: The New Data in Multimedia Research
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting
• Balanced Meta-Softmax for Long-Tailed Visual Recognition
• FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation
• Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
• Decoupling Representation and Classifier for Long-Tailed Recognition
• Rethinking the Value of Labels for Improving Class-Imbalanced Learning
• Model Compression with Adversarial Robustness: A Unified Optimization Framework
• Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
• AugMax: Adversarial Composition of Random Augmentations for Robust Training
• Topic Adaptation and Prototype Encoding for Few-Shot Visual Storytelling
• Long-tailed Distribution Adaptation
• Adversarial Learning with Margin-based Triplet Embedding Regularization

Cited by in corpus (7)

• A survey on learning from imbalanced data streams: taxonomy, challenges, empirical study, and reproducible experimental framework
• Feature Fusion from Head to Tail for Long-Tailed Visual Recognition
• Deep Learning Technique for Human Parsing: A Survey and Outlook
• Inverse Image Frequency for Long-tailed Image Recognition
• A dual-branch model with inter- and intra-branch contrastive loss for long-tailed recognition
• Frontiers in Intelligent Colonoscopy
• Model-based Transfer Learning for Automatic Optical Inspection based on domain discrepancy