# Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels

arXiv: https://arxiv.org/abs/2003.08264 · HTML: https://mlsanity.com/paper/2003.08264/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Mar 2020.

## Built on by (most cited first, 24 of 24)

- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Invariant Information Bottleneck for Domain Generalization](https://mlsanity.com/paper/2106.06333/) (2021)
- [Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.16765/) (2021)
- [CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2107.00085/) (2021)
- [Contrastive Domain Adaptation](https://mlsanity.com/paper/2103.15566/) (2021)
- [Feature Representation Learning for Unsupervised Cross-domain Image Retrieval](https://mlsanity.com/paper/2207.09721/) (2022)
- [Unsupervised Domain Adaptation for Video Transformers in Action Recognition](https://mlsanity.com/paper/2207.12842/) (2022)
- [Self-Rule to Multi-Adapt: Generalized Multi-source Feature Learning Using Unsupervised Domain Adaptation for Colorectal Cancer Tissue Detection](https://mlsanity.com/paper/2108.09178/) (2021)
- [CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domains](https://mlsanity.com/paper/2206.08083/) (2022)
- [Confidence-based Visual Dispersal for Few-shot Unsupervised Domain Adaptation](https://mlsanity.com/paper/2309.15575/) (2023)
- [Multi-source Few-shot Domain Adaptation](https://mlsanity.com/paper/2109.12391/) (2021)
- [Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild](https://mlsanity.com/paper/2403.14539/) (2024)
- [Low-confidence Samples Matter for Domain Adaptation](https://mlsanity.com/paper/2202.02802/) (2022)
- [Towards Unsupervised Sketch-based Image Retrieval](https://mlsanity.com/paper/2105.08237/) (2021)
- [Vision-aware Multimodal Prompt Tuning for Uploadable Multi-source Few-shot Domain Adaptation](https://mlsanity.com/paper/2503.06106/) (2025)
- [Data-Efficient CLIP-Powered Dual-Branch Networks for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2410.15811/) (2024)
- [Prototypical Cross-domain Knowledge Transfer for Cervical Dysplasia Visual Inspection](https://mlsanity.com/paper/2308.09983/) (2023)
- [Transferable-guided Attention Is All You Need for Video Domain Adaptation](https://mlsanity.com/paper/2407.01375/) (2024)
- [Gradient Regularized Contrastive Learning for Continual Domain Adaptation](https://mlsanity.com/paper/2103.12294/) (2021)
- [Recognition of Unseen Bird Species by Learning from Field Guides](https://mlsanity.com/paper/2206.01466/) (2022)
- [Adapting Self-Supervised Representations to Multi-Domain Setups](https://mlsanity.com/paper/2309.03999/) (2023)
- [Towards Unsupervised Representation Learning: Learning, Evaluating and Transferring Visual Representations](https://mlsanity.com/paper/2312.00101/) (2023)
- [Attention Residual Fusion Network with Contrast for Source-free Domain Adaptation](https://mlsanity.com/paper/2510.22142/) (2025)
- [Universal Latent Homeomorphic Manifolds: A Framework for Cross-Domain Representation Unification](https://mlsanity.com/paper/2601.09025/) (2026)

## Abstract (arXiv)

Existing unsupervised domain adaptation methods aim to transfer knowledge from a label-rich source domain to an unlabeled target domain. However, obtaining labels for some source domains may be very expensive, making complete labeling as used in prior work impractical. In this work, we investigate a new domain adaptation scenario with sparsely labeled source data, where only a few examples in the source domain have been labeled, while the target domain is unlabeled. We show that when labeled source examples are limited, existing methods often fail to learn discriminative features applicable for both source and target domains. We propose a novel Cross-Domain Self-supervised (CDS) learning approach for domain adaptation, which learns features that are not only domain-invariant but also class-discriminative. Our self-supervised learning method captures apparent visual similarity with in-domain self-supervision in a domain adaptive manner and performs cross-domain feature matching with across-domain self-supervision. In extensive experiments with three standard benchmark datasets, our method significantly boosts performance of target accuracy in the new target domain with few source labels and is even helpful on classical domain adaptation scenarios.