Certainty and Uncertainty Guided Active Domain Adaptation
Not on the map. Why?
Abstract (arXiv)
Active Domain Adaptation (ADA) adapts models to target domains by selectively labeling a few target samples. Existing ADA methods prioritize uncertain samples but overlook confident ones, which often match ground-truth. We find that incorporating confident predictions into the labeled set before active sampling reduces the search space and improves adaptation. To address this, we propose a collaborative framework that labels uncertain samples while treating highly confident predictions as ground truth. Our method combines Gaussian Process-based Active Sampling (GPAS) for identifying uncertain samples and Pseudo-Label-based Certain Sampling (PLCS) for confident ones, progressively enhancing adaptation. PLCS refines the search space, and GPAS reduces the domain gap, boosting the proportion of confident samples. Extensive experiments on Office-Home and DomainNet show that our approach outperforms state-of-the-art ADA methods.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 32 of its 47 references that are in the map. First posted on arXiv 26 May 2025.
Builds on
32 of 47 references.
References · 32
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2015Domain-Adversarial Training of Neural Networkscited by 3,023
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
- 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
- 2017Adversarial Discriminative Domain Adaptationcited by 1,309
- 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
- 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
- 2016An overview of gradient descent optimization algorithmscited by 1,021
- 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
- 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
- 2019Confidence Regularized Self-Trainingcited by 418
20 more
- 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
- 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 333
- 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
- 2017Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptationcited by 151
- 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
- 2020SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptationcited by 78
- 2019Active Adversarial Domain Adaptationcited by 73
- 2020Active Domain Adaptation via Clustering Uncertainty-weighted Embeddingscited by 71
- 2020Learning Invariant Representations and Risks for Semi-supervised Domain Adaptationcited by 69
- 2020Syn2Real Transfer Learning for Image Deraining using Gaussian Processescited by 62
- 2021Active Learning for Domain Adaptation: An Energy-Based Approachcited by 53
- 2023Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigmcited by 36
- 2023Active Prompt Learning in Vision Language Modelscited by 25
- 2023Entropic Open-set Active Learningcited by 22
- 2021S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptationcited by 19
- 2022Learning Distinctive Margin toward Active Domain Adaptationcited by 18
- 2021Discrepancy-Based Active Learning for Domain Adaptationcited by 16
- 2024Active Learning for Vision-Language Modelscited by 15
- 2025Filter Images First, Generate Instructions Later: Pre-Instruction Data Selection for Visual Instruction Tuningcited by 12
- 2019Natural and Adversarial Error Detection using Invariance to Image Transformationscited by 9
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.