# Extending and Analyzing Self-Supervised Learning Across Domains

arXiv: https://arxiv.org/abs/2004.11992 · HTML: https://mlsanity.com/paper/2004.11992/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Apr 2020.

## Built on by (most cited first, 20 of 20)

- [Assessing the State of Self-Supervised Human Activity Recognition using Wearables](https://mlsanity.com/paper/2202.12938/) (2022)
- [Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Data](https://mlsanity.com/paper/2106.07807/) (2021)
- [Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction](https://mlsanity.com/paper/2102.10106/) (2021)
- [A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification](https://mlsanity.com/paper/2104.00679/) (2021)
- [How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?](https://mlsanity.com/paper/2203.14221/) (2022)
- [Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation](https://mlsanity.com/paper/2207.13247/) (2022)
- [Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining and Consistency](https://mlsanity.com/paper/2101.12727/) (2021)
- [Rethinking Nearest Neighbors for Visual Classification](https://mlsanity.com/paper/2112.08459/) (2021)
- [Automatically Discovering Novel Visual Categories with Self-supervised Prototype Learning](https://mlsanity.com/paper/2208.00979/) (2022)
- [Nearest Neighbors Meet Deep Neural Networks for Point Cloud Analysis](https://mlsanity.com/paper/2303.00703/) (2023)
- [SEVERE++: Evaluating Benchmark Sensitivity in Generalization of Video Representation Learning](https://mlsanity.com/paper/2504.05706/) (2025)
- [Streaming Self-Training via Domain-Agnostic Unlabeled Images](https://mlsanity.com/paper/2104.03309/) (2021)
- [How Low Can We Go: Trading Memory for Error in Low-Precision Training](https://mlsanity.com/paper/2106.09686/) (2021)
- [Exploiting generative self-supervised learning for the assessment of biological images with lack of annotations: a COVID-19 case-study](https://mlsanity.com/paper/2107.07761/) (2021)
- [Self-Supervised Learning from Unlabeled Fundus Photographs Improves Segmentation of the Retina](https://mlsanity.com/paper/2108.02798/) (2021)
- [Exploring Self-Supervised Representation Learning For Low-Resource Medical Image Analysis](https://mlsanity.com/paper/2303.02245/) (2023)
- [Fine-grained Hand Gesture Recognition in Multi-viewpoint Hand Hygiene](https://mlsanity.com/paper/2109.02917/) (2021)
- [Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation](https://mlsanity.com/paper/2410.11271/) (2024)
- [Learning Rich Nearest Neighbor Representations from Self-supervised Ensembles](https://mlsanity.com/paper/2110.10293/) (2021)
- [Adapting Self-Supervised Representations to Multi-Domain Setups](https://mlsanity.com/paper/2309.03999/) (2023)

## Abstract (arXiv)

Self-supervised representation learning has achieved impressive results in recent years, with experiments primarily coming on ImageNet or other similarly large internet imagery datasets. There has been little to no work with these methods on other smaller domains, such as satellite, textural, or biological imagery. We experiment with several popular methods on an unprecedented variety of domains. We discover, among other findings, that Rotation is by far the most semantically meaningful task, with much of the performance of Jigsaw and Instance Discrimination being attributable to the nature of their induced distribution rather than semantic understanding. Additionally, there are several areas, such as fine-grain classification, where all tasks underperform. We quantitatively and qualitatively diagnose the reasons for these failures and successes via novel experiments studying pretext generalization, random labelings, and implicit dimensionality. Code and models are available at https://github.com/BramSW/Extending_SSRL_Across_Domains/.