# Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning

arXiv: https://arxiv.org/abs/2211.06612 · HTML: https://mlsanity.com/paper/2211.06612/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 50 references that are in the map.
- First posted on arXiv 12 Nov 2022.

## Builds on (most cited first, 30 of 40)

- [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)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID](https://mlsanity.com/paper/2006.02713/) (2020)
- [Local Aggregation for Unsupervised Learning of Visual Embeddings](https://mlsanity.com/paper/1903.12355/) (2019)
- [Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning](https://mlsanity.com/paper/1702.08811/) (2017)
- [Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data](https://mlsanity.com/paper/2010.03622/) (2020)
- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer](https://mlsanity.com/paper/2012.07297/) (2020)
- [Universal Domain Adaptation through Self Supervision](https://mlsanity.com/paper/2002.07953/) (2020)
- [Correlation Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1612.01939/) (2016)
- [Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations](https://mlsanity.com/paper/2003.12237/) (2020)
- [Gradually Vanishing Bridge for Adversarial Domain Adaptation](https://mlsanity.com/paper/2003.13183/) (2020)

## Built on by (most cited first, 30 of 53)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [LEAD: Learning Decomposition for Source-free Universal Domain Adaptation](https://mlsanity.com/paper/2403.03421/) (2024)
- [Diversifying Spatial-Temporal Perception for Video Domain Generalization](https://mlsanity.com/paper/2310.17942/) (2023)
- [SF(DA)2: Source-free Domain Adaptation Through the Lens of Data Augmentation](https://mlsanity.com/paper/2403.10834/) (2024)
- [Consistency Regularization for Generalizable Source-free Domain Adaptation](https://mlsanity.com/paper/2308.01587/) (2023)
- [Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation](https://mlsanity.com/paper/2403.01467/) (2024)
- [Divide and Adapt: Active Domain Adaptation via Customized Learning](https://mlsanity.com/paper/2307.11618/) (2023)
- [Bayesian-guided Label Mapping for Visual Reprogramming](https://mlsanity.com/paper/2410.24018/) (2024)
- [Activate and Reject: Towards Safe Domain Generalization under Category Shift](https://mlsanity.com/paper/2310.04724/) (2023)
- [Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2401.11448/) (2024)
- [SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network](https://mlsanity.com/paper/2405.14398/) (2024)
- [Distribution Shift Matters for Knowledge Distillation with Webly Collected Images](https://mlsanity.com/paper/2307.11469/) (2023)
- [Direct Distillation between Different Domains](https://mlsanity.com/paper/2401.06826/) (2024)
- [Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation](https://mlsanity.com/paper/2406.06813/) (2024)
- [Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence](https://mlsanity.com/paper/2407.18899/) (2024)
- [A Layer Selection Approach to Test Time Adaptation](https://mlsanity.com/paper/2404.03784/) (2024)
- [ToCoAD: Two-Stage Contrastive Learning for Industrial Anomaly Detection](https://mlsanity.com/paper/2407.01312/) (2024)
- [Rank and Align: Towards Effective Source-free Graph Domain Adaptation](https://mlsanity.com/paper/2408.12185/) (2024)
- [ReC-TTT: Contrastive Feature Reconstruction for Test-Time Training](https://mlsanity.com/paper/2411.17869/) (2024)
- [CoSDA: Continual Source-Free Domain Adaptation](https://mlsanity.com/paper/2304.06627/) (2023)
- [GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning](https://mlsanity.com/paper/2403.14410/) (2024)
- [Temporal Source Recovery for Time-Series Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2409.19635/) (2024)
- [Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data](https://mlsanity.com/paper/2412.13757/) (2024)
- [Do Machine Learning Models Learn Statistical Rules Inferred from Data?](https://mlsanity.com/paper/2303.01433/) (2023)
- [Target-agnostic Source-free Domain Adaptation for Regression Tasks](https://mlsanity.com/paper/2312.00540/) (2023)
- [Fuzzy-aware Loss for Source-free Domain Adaptation in Visual Emotion Recognition](https://mlsanity.com/paper/2501.15519/) (2025)
- [HAROOD: A Benchmark for Out-of-distribution Generalization in Sensor-based Human Activity Recognition](https://mlsanity.com/paper/2512.10807/) (2025)
- [Incorporating Pre-training Data Matters in Unsupervised Domain Adaptation](https://mlsanity.com/paper/2308.03097/) (2023)
- [Domain Adaptation for Large-Vocabulary Object Detectors](https://mlsanity.com/paper/2401.06969/) (2024)
- [Structural Alignment Improves Graph Test-Time Adaptation](https://mlsanity.com/paper/2502.18334/) (2025)

## Abstract (arXiv)

We investigate a practical domain adaptation task, called source-free domain adaptation (SFUDA), where the source-pretrained model is adapted to the target domain without access to the source data. Existing techniques mainly leverage self-supervised pseudo labeling to achieve class-wise global alignment [1] or rely on local structure extraction that encourages feature consistency among neighborhoods [2]. While impressive progress has been made, both lines of methods have their own drawbacks - the "global" approach is sensitive to noisy labels while the "local" counterpart suffers from source bias. In this paper, we present Divide and Contrast (DaC), a new paradigm for SFUDA that strives to connect the good ends of both worlds while bypassing their limitations. Based on the prediction confidence of the source model, DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals under an adaptive contrastive learning framework. Specifically, the source-like samples are utilized for learning global class clustering thanks to their relatively clean labels. The more noisy target-specific data are harnessed at the instance level for learning the intrinsic local structures. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch. Extensive experiments on VisDA, Office-Home, and the more challenging DomainNet have verified the superior performance of DaC over current state-of-the-art approaches. The code is available at https://github.com/ZyeZhang/DaC.git.