# Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence

arXiv: https://arxiv.org/abs/2407.18899 · HTML: https://mlsanity.com/paper/2407.18899/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 68 references that are in the map.
- First posted on arXiv 26 Jul 2024.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models](https://mlsanity.com/paper/2309.03883/) (2023)
- [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019)
- [What's the Point: Semantic Segmentation with Point Supervision](https://mlsanity.com/paper/1506.02106/) (2015)
- [Universal Source-Free Domain Adaptation](https://mlsanity.com/paper/2004.04393/) (2020)
- [A DIRT-T Approach to Unsupervised Domain Adaptation](https://mlsanity.com/paper/1802.08735/) (2018)
- [Domain-Specific Batch Normalization for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1906.03950/) (2019)
- [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)
- [Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2110.03374/) (2021)
- [Open Set Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1804.10427/) (2018)
- [Learning Discrete Representations via Information Maximizing Self-Augmented Training](https://mlsanity.com/paper/1702.08720/) (2017)
- [Partial Adversarial Domain Adaptation](https://mlsanity.com/paper/1808.04205/) (2018)
- [Few-Shot Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.02536/) (2017)
- [Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation](https://mlsanity.com/paper/2106.15326/) (2021)
- [Source-Free Domain Adaptation via Distribution Estimation](https://mlsanity.com/paper/2204.11257/) (2022)
- [Domain Adaptation without Source Data](https://mlsanity.com/paper/2007.01524/) (2020)
- [Active Adversarial Domain Adaptation](https://mlsanity.com/paper/1904.07848/) (2019)
- [Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings](https://mlsanity.com/paper/2010.08666/) (2020)
- [Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation](https://mlsanity.com/paper/2004.06042/) (2020)
- [Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning](https://mlsanity.com/paper/2211.06612/) (2022)
- [Deep Residual Correction Network for Partial Domain Adaptation](https://mlsanity.com/paper/2004.04914/) (2020)

## Built on by (most cited first, 8 of 8)

- [Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations](https://mlsanity.com/paper/2507.09500/) (2025)
- [ViLAaD: Enhancing "Attracting and Dispersing'' Source-Free Domain Adaptation with Vision-and-Language Model](https://mlsanity.com/paper/2503.23529/) (2025)
- [Cream of the Crop: Harvesting Rich, Scalable and Transferable Multi-Modal Data for Instruction Fine-Tuning](https://mlsanity.com/paper/2503.13383/) (2025)
- [Neutralizing Token Aggregation via Information Augmentation for Efficient Test-Time Adaptation](https://mlsanity.com/paper/2508.03388/) (2025)
- [ProCal: Probability Calibration for Neighborhood-Guided Source-Free Domain Adaptation](https://mlsanity.com/paper/2603.18764/) (2026)
- [SCoDA: Self-supervised Continual Domain Adaptation](https://mlsanity.com/paper/2509.09935/) (2025)
- [Simple Supervision Is Hard to Beat: A Bitter Lesson from Sparse Target Labels in Domain-Adaptive Object Detection](https://mlsanity.com/paper/2606.30795/) (2026)
- [Towards Purified Multi-Label Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2608.25653/) (2026)

## Abstract (arXiv)

Domain Adaptation (DA) facilitates knowledge transfer from a source domain to a related target domain. This paper investigates a practical DA paradigm, namely Source data-Free Active Domain Adaptation (SFADA), where source data becomes inaccessible during adaptation, and a minimum amount of annotation budget is available in the target domain. Without referencing the source data, new challenges emerge in identifying the most informative target samples for labeling, establishing cross-domain alignment during adaptation, and ensuring continuous performance improvements through the iterative query-and-adaptation process. In response, we present learn from the learnt (LFTL), a novel paradigm for SFADA to leverage the learnt knowledge from the source pretrained model and actively iterated models without extra overhead. We propose Contrastive Active Sampling to learn from the hypotheses of the preceding model, thereby querying target samples that are both informative to the current model and persistently challenging throughout active learning. During adaptation, we learn from features of actively selected anchors obtained from previous intermediate models, so that the Visual Persistence-guided Adaptation can facilitate feature distribution alignment and active sample exploitation. Extensive experiments on three widely-used benchmarks show that our LFTL achieves state-of-the-art performance, superior computational efficiency and continuous improvements as the annotation budget increases. Our code is available at https://github.com/lyumengyao/lftl.