Deep Long-Tailed Learning: A Survey

By Yifan Zhang, Bingyi Kang, Bryan Hooi, Shuicheng Yan, Jiashi Feng. 2021

927 citations recorded by the source corpus.

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 article 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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Han-Jia Ye
2. De-chuan Zhan
3. Da-Wei Zhou
4. Ziwei Liu
5. Qiwen Wang
6. Yifan Zhang
7. Mingkui Tan
8. Shuaicheng Niu

In Computer Vision and Pattern Recognition

1. Han-Jia Ye
2. De-chuan Zhan
3. Mingkui Tan
4. Da-Wei Zhou
5. Jiashi Feng
6. Ziwei Liu
7. Chuang Gan
8. Yifan Zhang

Citations in the corpus

• Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation (2022, background): “Step 6 [50,51,52,53,54,55,56,57,58,59] Flowers, Lamp Shade, Spoon, Candles, Clipboards Scissors, TV, Curtains, Fork, Soda”
• Deep Class-Incremental Learning: A Survey (2023, background): “Simultaneously, the data-imbalance problem [135], [136] also occurs due to the gap between the few-shot exemplars and the many-shot training set.”
• Class-Incremental Learning: A Survey (2023, result): “The shade color in the last column denotes the subcategory, which is consistent with Figure 3.”
• On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective (2023, background): “, 2014), long-tailed samples (Zhang et al., 2021), noisy inputs (Natarajan et al.”
• Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning (2021, methodology): “[73] Yifan Zhang, Bingyi Kang, Bryan Hooi, Shuicheng Yan, and Jiashi Feng.”
• A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, background): “However, most existing artificial intelligence (AI) models only imitate the learning procedure from experiences while ignoring the former [1], [2], thus making them less explainable and worse performances.”