Data to 14 Oct 2026

Semi-supervised Domain Adaptation via Minimax Entropy

arXiv 1904.06487 ↗First posted 13 Apr 2019cs.CVcited by 335

Not on the map. Why?

Abstract (arXiv)

Contemporary domain adaptation methods are very effective at aligning feature distributions of source and target domains without any target supervision. However, we show that these techniques perform poorly when even a few labeled examples are available in the target. To address this semi-supervised domain adaptation (SSDA) setting, we propose a novel Minimax Entropy (MME) approach that adversarially optimizes an adaptive few-shot model. Our base model consists of a feature encoding network, followed by a classification layer that computes the features' similarity to estimated prototypes (representatives of each class). Adaptation is achieved by alternately maximizing the conditional entropy of unlabeled target data with respect to the classifier and minimizing it with respect to the feature encoder. We empirically demonstrate the superiority of our method over many baselines, including conventional feature alignment and few-shot methods, setting a new state of the art for SSDA.

Key facts. Cited by 335 papers in the map (data through 14 Oct 2026). First posted on arXiv 13 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 87; 2022: 64; 2023: 81; 2024: 50; 2025: 32; 2026: 21.

335 papers.

Sort:

By area:

2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 382
2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
2022Contrastive Test-Time Adaptationcited by 261
2021Learning to Diversify for Single Domain Generalizationcited by 170
2025The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoningcited by 166
2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
2021Predicting with Confidence on Unseen Distributionscited by 116
2021AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptationcited by 104
2022Robust Mean Teacher for Continual and Gradual Test-Time Adaptationcited by 104
2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
2025Maximizing Confidence Alone Improves Reasoningcited by 100
2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98

38 more

2022Source-Free Domain Adaptation via Distribution Estimationcited by 97
2022Visual Prompt Tuning for Test-time Domain Adaptationcited by 97
2021Unsupervised Domain Adaptation of Object Detectors: A Surveycited by 93
2021Invariant Information Bottleneck for Domain Generalizationcited by 86
2021Delving Deep into the Generalization of Vision Transformers under Distribution Shiftscited by 85
2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
2021Self-Supervised Pretraining Improves Self-Supervised Pretrainingcited by 82
2021TVT: Transferable Vision Transformer for Unsupervised Domain Adaptationcited by 81
2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
2021VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptationcited by 69
2021Mining Latent Classes for Few-shot Segmentationcited by 69
2021Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptationcited by 67
2022A Broad Study of Pre-training for Domain Generalization and Adaptationcited by 65
2023Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptationcited by 65
2023Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correctioncited by 65
2021A Prototype-Oriented Framework for Unsupervised Domain Adaptationcited by 62
2023PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalizationcited by 59
2023Source-Free Domain Adaptation with Frozen Multimodal Foundation Modelcited by 55
2021Active Learning for Domain Adaptation: An Energy-Based Approachcited by 53
2022Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learningcited by 53
2021CLDA: Contrastive Learning for Semi-Supervised Domain Adaptationcited by 52
2023C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptationcited by 50
2021Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixingcited by 49
2021Style Normalization and Restitution for Domain Generalization and Adaptationcited by 46
2021Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Densitycited by 44
2021Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentationcited by 40
2021Feature Stylization and Domain-aware Contrastive Learning for Domain Generalizationcited by 40
2021Qimera: Data-free Quantization with Synthetic Boundary Supporting Samplescited by 40
2021Multi-Objective Meta Learningcited by 39
2021Cross-category Video Highlight Detection via Set-based Learningcited by 38
2022Adversarial Feature Augmentation for Cross-domain Few-shot Classificationcited by 36
2023ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptationcited by 35
2021Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentationcited by 33
2021ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptationcited by 33
2021LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentationcited by 33
2021Unsupervised Domain Generalization by Learning a Bridge Across Domainscited by 33
2021A Style and Semantic Memory Mechanism for Domain Generalizationcited by 32
2021ECACL: A Holistic Framework for Semi-Supervised Domain Adaptationcited by 31

50 most cited of 335 All 335 (JSON)