# Self-supervised Learning is More Robust to Dataset Imbalance

arXiv: https://arxiv.org/abs/2110.05025 · HTML: https://mlsanity.com/paper/2110.05025/

## Key facts

- Cited by 123 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 74 references that are in the map.
- First posted on arXiv 11 Oct 2021.

## Builds on (most cited first, 30 of 53)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [A Theoretical Analysis of Contrastive Unsupervised Representation Learning](https://mlsanity.com/paper/1902.09229/) (2019)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss](https://mlsanity.com/paper/2106.04156/) (2021)
- [Long-tailed Recognition by Routing Diverse Distribution-Aware Experts](https://mlsanity.com/paper/2010.01809/) (2020)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [Understanding self-supervised Learning Dynamics without Contrastive Pairs](https://mlsanity.com/paper/2102.06810/) (2021)
- [What is the Effect of Importance Weighting in Deep Learning?](https://mlsanity.com/paper/1812.03372/) (2018)
- [Rethinking the Value of Labels for Improving Class-Imbalanced Learning](https://mlsanity.com/paper/2006.07529/) (2020)
- [Self-supervised Pretraining of Visual Features in the Wild](https://mlsanity.com/paper/2103.01988/) (2021)

## Built on by (most cited first, 30 of 123)

- [Improving Out-of-Distribution Robustness via Selective Augmentation](https://mlsanity.com/paper/2201.00299/) (2022)
- [Discover and Cure: Concept-aware Mitigation of Spurious Correlation](https://mlsanity.com/paper/2305.00650/) (2023)
- [BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning](https://mlsanity.com/paper/2303.14773/) (2023)
- [MEDFAIR: Benchmarking Fairness for Medical Imaging](https://mlsanity.com/paper/2210.01725/) (2022)
- [Assessing the State of Self-Supervised Human Activity Recognition using Wearables](https://mlsanity.com/paper/2202.12938/) (2022)
- [Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail Data](https://mlsanity.com/paper/2303.13664/) (2023)
- [Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty](https://mlsanity.com/paper/2202.01339/) (2022)
- [Are Vision Transformers Robust to Spurious Correlations?](https://mlsanity.com/paper/2203.09125/) (2022)
- [How Re-sampling Helps for Long-Tail Learning?](https://mlsanity.com/paper/2310.18236/) (2023)
- [Learning Imbalanced Data with Vision Transformers](https://mlsanity.com/paper/2212.02015/) (2022)
- [SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving](https://mlsanity.com/paper/2206.14116/) (2022)
- [CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition](https://mlsanity.com/paper/2302.05499/) (2023)
- [Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression](https://mlsanity.com/paper/2305.16536/) (2023)
- [Understanding Why Generalized Reweighting Does Not Improve Over ERM](https://mlsanity.com/paper/2201.12293/) (2022)
- [Geodesic Multi-Modal Mixup for Robust Fine-Tuning](https://mlsanity.com/paper/2203.03897/) (2022)
- [The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning](https://mlsanity.com/paper/2303.00106/) (2023)
- [Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks](https://mlsanity.com/paper/2309.17002/) (2023)
- [Contrastive Learning with Boosted Memorization](https://mlsanity.com/paper/2205.12693/) (2022)
- [Group Robust Classification Without Any Group Information](https://mlsanity.com/paper/2310.18555/) (2023)
- [How Robust is Unsupervised Representation Learning to Distribution Shift?](https://mlsanity.com/paper/2206.08871/) (2022)
- [Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works](https://mlsanity.com/paper/2211.08129/) (2022)
- [Transferring Fairness under Distribution Shifts via Fair Consistency Regularization](https://mlsanity.com/paper/2206.12796/) (2022)
- [A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing](https://mlsanity.com/paper/2210.04675/) (2022)
- [When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method](https://mlsanity.com/paper/2211.10955/) (2022)
- [Understanding Contrastive Learning via Distributionally Robust Optimization](https://mlsanity.com/paper/2310.11048/) (2023)
- [A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias](https://mlsanity.com/paper/2303.13500/) (2023)
- [Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression](https://mlsanity.com/paper/2306.00788/) (2023)
- [On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning](https://mlsanity.com/paper/2306.04934/) (2023)
- [Investigating the Benefits of Projection Head for Representation Learning](https://mlsanity.com/paper/2403.11391/) (2024)
- [What shapes the loss landscape of self-supervised learning?](https://mlsanity.com/paper/2210.00638/) (2022)

## Abstract (arXiv)

Self-supervised learning (SSL) is a scalable way to learn general visual representations since it learns without labels. However, large-scale unlabeled datasets in the wild often have long-tailed label distributions, where we know little about the behavior of SSL. In this work, we systematically investigate self-supervised learning under dataset imbalance. First, we find out via extensive experiments that off-the-shelf self-supervised representations are already more robust to class imbalance than supervised representations. The performance gap between balanced and imbalanced pre-training with SSL is significantly smaller than the gap with supervised learning, across sample sizes, for both in-domain and, especially, out-of-domain evaluation. Second, towards understanding the robustness of SSL, we hypothesize that SSL learns richer features from frequent data: it may learn label-irrelevant-but-transferable features that help classify the rare classes and downstream tasks. In contrast, supervised learning has no incentive to learn features irrelevant to the labels from frequent examples. We validate this hypothesis with semi-synthetic experiments and theoretical analyses on a simplified setting. Third, inspired by the theoretical insights, we devise a re-weighted regularization technique that consistently improves the SSL representation quality on imbalanced datasets with several evaluation criteria, closing the small gap between balanced and imbalanced datasets with the same number of examples.