# Learning Distinctive Margin toward Active Domain Adaptation

arXiv: https://arxiv.org/abs/2203.05738 · HTML: https://mlsanity.com/paper/2203.05738/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 40 references that are in the map.
- First posted on arXiv 11 Mar 2022.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1803.10081/) (2018)
- [Contextual Diversity for Active Learning](https://mlsanity.com/paper/2008.05723/) (2020)
- [Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations](https://mlsanity.com/paper/2003.12237/) (2020)
- [Task-Aware Variational Adversarial Active Learning](https://mlsanity.com/paper/2002.04709/) (2020)
- [Domain Adaptation with Auxiliary Target Domain-Oriented Classifier](https://mlsanity.com/paper/2007.04171/) (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)
- [Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation](https://mlsanity.com/paper/2010.04647/) (2020)
- [State-Relabeling Adversarial Active Learning](https://mlsanity.com/paper/2004.04943/) (2020)
- [ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2104.09136/) (2021)
- [VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learning](https://mlsanity.com/paper/2003.11249/) (2020)
- [S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation](https://mlsanity.com/paper/2109.08901/) (2021)
- [Cost-Effective Training of Deep CNNs with Active Model Adaptation](https://mlsanity.com/paper/1802.05394/) (2018)

## Built on by (most cited first, 18 of 18)

- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection](https://mlsanity.com/paper/2303.05886/) (2023)
- [Combating Label Distribution Shift for Active Domain Adaptation](https://mlsanity.com/paper/2208.06604/) (2022)
- [Evidential Uncertainty Quantification: A Variance-Based Perspective](https://mlsanity.com/paper/2311.11367/) (2023)
- [Divide and Adapt: Active Domain Adaptation via Customized Learning](https://mlsanity.com/paper/2307.11618/) (2023)
- [Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence](https://mlsanity.com/paper/2407.18899/) (2024)
- [Generalized Universal Domain Adaptation with Generative Flow Networks](https://mlsanity.com/paper/2305.04466/) (2023)
- [Local Context-Aware Active Domain Adaptation](https://mlsanity.com/paper/2208.12856/) (2022)
- [Open-Set Automatic Target Recognition](https://mlsanity.com/paper/2211.05883/) (2022)
- [Spectral Transfer Guided Active Domain Adaptation For Thermal Imagery](https://mlsanity.com/paper/2304.07031/) (2023)
- [Certainty and Uncertainty Guided Active Domain Adaptation](https://mlsanity.com/paper/2505.19421/) (2025)
- [Is user feedback always informative? Retrieval Latent Defending for Semi-Supervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2407.15383/) (2024)
- [Generative Active Testing: Efficient LLM Evaluation via Proxy Task Adaptation](https://mlsanity.com/paper/2603.19264/) (2026)
- [Unsupervised Domain Adaptation via Style-Aware Self-intermediate Domain](https://mlsanity.com/paper/2209.01870/) (2022)
- [Density Matters: Improved Core-set for Active Domain Adaptive Segmentation](https://mlsanity.com/paper/2312.09595/) (2023)
- [D3GU: Multi-Target Active Domain Adaptation via Enhancing Domain Alignment](https://mlsanity.com/paper/2401.05465/) (2024)
- [Source-free Active Domain Adaptation for Diabetic Retinopathy Grading Based on Ultra-wide-field Fundus Image](https://mlsanity.com/paper/2309.10619/) (2023)
- [GALA: A GlobAl-LocAl Approach for Multi-Source Active Domain Adaptation](https://mlsanity.com/paper/2510.22214/) (2025)

## Abstract (arXiv)

Despite plenty of efforts focusing on improving the domain adaptation ability (DA) under unsupervised or few-shot semi-supervised settings, recently the solution of active learning started to attract more attention due to its suitability in transferring model in a more practical way with limited annotation resource on target data. Nevertheless, most active learning methods are not inherently designed to handle domain gap between data distribution, on the other hand, some active domain adaptation methods (ADA) usually requires complicated query functions, which is vulnerable to overfitting. In this work, we propose a concise but effective ADA method called Select-by-Distinctive-Margin (SDM), which consists of a maximum margin loss and a margin sampling algorithm for data selection. We provide theoretical analysis to show that SDM works like a Support Vector Machine, storing hard examples around decision boundaries and exploiting them to find informative and transferable data. In addition, we propose two variants of our method, one is designed to adaptively adjust the gradient from margin loss, the other boosts the selectivity of margin sampling by taking the gradient direction into account. We benchmark SDM with standard active learning setting, demonstrating our algorithm achieves competitive results with good data scalability. Code is available at https://github.com/TencentYoutuResearch/ActiveLearning-SDM