# Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective

arXiv: https://arxiv.org/abs/2003.10780 · HTML: https://mlsanity.com/paper/2003.10780/

## Key facts

- Cited by 143 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Mar 2020.

## Built on by (most cited first, 30 of 143)

- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Parametric Contrastive Learning](https://mlsanity.com/paper/2107.12028/) (2021)
- [CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2102.09559/) (2021)
- [Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification](https://mlsanity.com/paper/2103.14267/) (2021)
- [Self-supervised Learning is More Robust to Dataset Imbalance](https://mlsanity.com/paper/2110.05025/) (2021)
- [Federated Learning with Label Distribution Skew via Logits Calibration](https://mlsanity.com/paper/2209.00189/) (2022)
- [Long-Tailed Recognition via Weight Balancing](https://mlsanity.com/paper/2203.14197/) (2022)
- [MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2103.12579/) (2021)
- [ResLT: Residual Learning for Long-tailed Recognition](https://mlsanity.com/paper/2101.10633/) (2021)
- [Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition](https://mlsanity.com/paper/2107.09249/) (2021)
- [Unsupervised Domain Adaptation of Object Detectors: A Survey](https://mlsanity.com/paper/2105.13502/) (2021)
- [Balanced MSE for Imbalanced Visual Regression](https://mlsanity.com/paper/2203.16427/) (2022)
- [Learning Affordance Grounding from Exocentric Images](https://mlsanity.com/paper/2203.09905/) (2022)
- [A Survey on Long-Tailed Visual Recognition](https://mlsanity.com/paper/2205.13775/) (2022)
- [Self Supervision to Distillation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2109.04075/) (2021)
- [Distilling Virtual Examples for Long-tailed Recognition](https://mlsanity.com/paper/2103.15042/) (2021)
- [LPT: Long-tailed Prompt Tuning for Image Classification](https://mlsanity.com/paper/2210.01033/) (2022)
- [Learning of Visual Relations: The Devil is in the Tails](https://mlsanity.com/paper/2108.09668/) (2021)
- [ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning](https://mlsanity.com/paper/2110.10368/) (2021)
- [VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2111.13579/) (2021)
- [DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data](https://mlsanity.com/paper/2105.02340/) (2021)
- [Nested Collaborative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2203.15359/) (2022)
- [Adversarial Robustness under Long-Tailed Distribution](https://mlsanity.com/paper/2104.02703/) (2021)
- [On Exposing the Challenging Long Tail in Future Prediction of Traffic Actors](https://mlsanity.com/paper/2103.12474/) (2021)
- [Understanding Imbalanced Semantic Segmentation Through Neural Collapse](https://mlsanity.com/paper/2301.01100/) (2023)
- [Generalized Parametric Contrastive Learning](https://mlsanity.com/paper/2209.12400/) (2022)
- [EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generation](https://mlsanity.com/paper/2305.18891/) (2023)
- [Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective](https://mlsanity.com/paper/2111.03874/) (2021)
- [Faster Meta Update Strategy for Noise-Robust Deep Learning](https://mlsanity.com/paper/2104.15092/) (2021)
- [Robust Long-Tailed Learning under Label Noise](https://mlsanity.com/paper/2108.11569/) (2021)

## Abstract (arXiv)

Object frequency in the real world often follows a power law, leading to a mismatch between datasets with long-tailed class distributions seen by a machine learning model and our expectation of the model to perform well on all classes. We analyze this mismatch from a domain adaptation point of view. First of all, we connect existing class-balanced methods for long-tailed classification to target shift, a well-studied scenario in domain adaptation. The connection reveals that these methods implicitly assume that the training data and test data share the same class-conditioned distribution, which does not hold in general and especially for the tail classes. While a head class could contain abundant and diverse training examples that well represent the expected data at inference time, the tail classes are often short of representative training data. To this end, we propose to augment the classic class-balanced learning by explicitly estimating the differences between the class-conditioned distributions with a meta-learning approach. We validate our approach with six benchmark datasets and three loss functions.