# Joint Contrastive Learning for Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/2006.10297 · HTML: https://mlsanity.com/paper/2006.10297/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2020.

## Built on by (most cited first, 25 of 25)

- [Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors](https://mlsanity.com/paper/2403.07366/) (2024)
- [Cross-domain Contrastive Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.05528/) (2021)
- [Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations](https://mlsanity.com/paper/2204.02683/) (2022)
- [Contrastive Domain Adaptation](https://mlsanity.com/paper/2103.15566/) (2021)
- [CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial Learning](https://mlsanity.com/paper/2109.14778/) (2021)
- [GeoNet: Benchmarking Unsupervised Adaptation across Geographies](https://mlsanity.com/paper/2303.15443/) (2023)
- [MemSAC: Memory Augmented Sample Consistency for Large Scale Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.12389/) (2022)
- [Unsupervised Domain Adaptation for Video Transformers in Action Recognition](https://mlsanity.com/paper/2207.12842/) (2022)
- [Domain Adaptation via Maximizing Surrogate Mutual Information](https://mlsanity.com/paper/2110.12184/) (2021)
- [Learn to Ignore: Domain Adaptation for Multi-Site MRI Analysis](https://mlsanity.com/paper/2110.06803/) (2021)
- [Domain Confused Contrastive Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.04564/) (2022)
- [Tell, Don't Show!: Language Guidance Eases Transfer Across Domains in Images and Videos](https://mlsanity.com/paper/2403.05535/) (2024)
- [Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation](https://mlsanity.com/paper/2403.10911/) (2024)
- [Anomaly Detection in IR Images of PV Modules using Supervised Contrastive Learning](https://mlsanity.com/paper/2112.02922/) (2021)
- [Unsupervised domain adaptation via coarse-to-fine feature alignment method using contrastive learning](https://mlsanity.com/paper/2103.12371/) (2021)
- [Review-Based Domain Disentanglement without Duplicate Users or Contexts for Cross-Domain Recommendation](https://mlsanity.com/paper/2110.12648/) (2021)
- [COSTAR: Improved Temporal Counterfactual Estimation with Self-Supervised Learning](https://mlsanity.com/paper/2311.00886/) (2023)
- [Prototypical Cross-domain Knowledge Transfer for Cervical Dysplasia Visual Inspection](https://mlsanity.com/paper/2308.09983/) (2023)
- [Trustworthy Representation Learning Across Domains](https://mlsanity.com/paper/2308.12315/) (2023)
- [Transferable-guided Attention Is All You Need for Video Domain Adaptation](https://mlsanity.com/paper/2407.01375/) (2024)
- [ETAGE: Enhanced Test Time Adaptation with Integrated Entropy and Gradient Norms for Robust Model Performance](https://mlsanity.com/paper/2409.09251/) (2024)
- [Gradient Regularized Contrastive Learning for Continual Domain Adaptation](https://mlsanity.com/paper/2103.12294/) (2021)
- [Bures Joint Distribution Alignment with Dynamic Margin for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2203.06836/) (2022)
- [Attention Residual Fusion Network with Contrast for Source-free Domain Adaptation](https://mlsanity.com/paper/2510.22142/) (2025)
- [Cross-Temperature Defect Identification in Atomistic Simulations via Multi-Level Domain Alignment](https://mlsanity.com/paper/2608.22074/) (2026)

## Abstract (arXiv)

Enhancing feature transferability by matching marginal distributions has led to improvements in domain adaptation, although this is at the expense of feature discrimination. In particular, the ideal joint hypothesis error in the target error upper bound, which was previously considered to be minute, has been found to be significant, impairing its theoretical guarantee. In this paper, we propose an alternative upper bound on the target error that explicitly considers the joint error to render it more manageable. With the theoretical analysis, we suggest a joint optimization framework that combines the source and target domains. Further, we introduce Joint Contrastive Learning (JCL) to find class-level discriminative features, which is essential for minimizing the joint error. With a solid theoretical framework, JCL employs contrastive loss to maximize the mutual information between a feature and its label, which is equivalent to maximizing the Jensen-Shannon divergence between conditional distributions. Experiments on two real-world datasets demonstrate that JCL outperforms the state-of-the-art methods.