# Divide and Adapt: Active Domain Adaptation via Customized Learning

arXiv: https://arxiv.org/abs/2307.11618 · HTML: https://mlsanity.com/paper/2307.11618/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 21 Jul 2023.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [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)
- [Unsupervised Label Noise Modeling and Loss Correction](https://mlsanity.com/paper/1904.11238/) (2019)
- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [Cost-Effective Active Learning for Deep Image Classification](https://mlsanity.com/paper/1701.03551/) (2017)
- [Automatically Discovering and Learning New Visual Categories with Ranking Statistics](https://mlsanity.com/paper/2002.05714/) (2020)
- [Influence Selection for Active Learning](https://mlsanity.com/paper/2108.09331/) (2021)
- [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)
- [Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2104.09415/) (2021)
- [Active Learning by Feature Mixing](https://mlsanity.com/paper/2203.07034/) (2022)
- [Active Learning for Domain Adaptation: An Energy-Based Approach](https://mlsanity.com/paper/2112.01406/) (2021)
- [Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning](https://mlsanity.com/paper/2211.06612/) (2022)
- [Multi-level Consistency Learning for Semi-supervised Domain Adaptation](https://mlsanity.com/paper/2205.04066/) (2022)
- [Learning Distinctive Margin toward Active Domain Adaptation](https://mlsanity.com/paper/2203.05738/) (2022)
- [Cost-Effective Training of Deep CNNs with Active Model Adaptation](https://mlsanity.com/paper/1802.05394/) (2018)

## Built on by (most cited first, 13 of 13)

- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection](https://mlsanity.com/paper/2406.00510/) (2024)
- [Unsupervised Domain Adaptation via Domain-Adaptive Diffusion](https://mlsanity.com/paper/2308.13893/) (2023)
- [FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels](https://mlsanity.com/paper/2312.12263/) (2023)
- [Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2401.11448/) (2024)
- [AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning](https://mlsanity.com/paper/2406.00480/) (2024)
- [Unified modality separation: A vision-language framework for unsupervised domain adaptation](https://mlsanity.com/paper/2508.04987/) (2025)
- [Weakly Supervised Test-Time Domain Adaptation for Object Detection](https://mlsanity.com/paper/2407.05607/) (2024)
- [Is user feedback always informative? Retrieval Latent Defending for Semi-Supervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2407.15383/) (2024)
- [Annotation-Efficient Polyp Segmentation via Active Learning](https://mlsanity.com/paper/2403.14350/) (2024)
- [Stratified Domain Adaptation: A Progressive Self-Training Approach for Scene Text Recognition](https://mlsanity.com/paper/2410.09913/) (2024)
- [Enhancing Skin Lesion Classification Generalization with Active Domain Adaptation](https://mlsanity.com/paper/2412.00702/) (2024)
- [Active Learning Methods for Efficient Data Utilization and Model Performance Enhancement](https://mlsanity.com/paper/2504.16136/) (2025)

## Abstract (arXiv)

Active domain adaptation (ADA) aims to improve the model adaptation performance by incorporating active learning (AL) techniques to label a maximally-informative subset of target samples. Conventional AL methods do not consider the existence of domain shift, and hence, fail to identify the truly valuable samples in the context of domain adaptation. To accommodate active learning and domain adaption, the two naturally different tasks, in a collaborative framework, we advocate that a customized learning strategy for the target data is the key to the success of ADA solutions. We present Divide-and-Adapt (DiaNA), a new ADA framework that partitions the target instances into four categories with stratified transferable properties. With a novel data subdivision protocol based on uncertainty and domainness, DiaNA can accurately recognize the most gainful samples. While sending the informative instances for annotation, DiaNA employs tailored learning strategies for the remaining categories. Furthermore, we propose an informativeness score that unifies the data partitioning criteria. This enables the use of a Gaussian mixture model (GMM) to automatically sample unlabeled data into the proposed four categories. Thanks to the "divideand-adapt" spirit, DiaNA can handle data with large variations of domain gap. In addition, we show that DiaNA can generalize to different domain adaptation settings, such as unsupervised domain adaptation (UDA), semi-supervised domain adaptation (SSDA), source-free domain adaptation (SFDA), etc.