# Semi-supervised Domain Adaptation via Minimax Entropy

arXiv: https://arxiv.org/abs/1904.06487 · HTML: https://mlsanity.com/paper/1904.06487/

## Key facts

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

## Built on by (most cited first, 30 of 335)

- [Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models](https://mlsanity.com/paper/2209.07511/) (2022)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [Contrastive Test-Time Adaptation](https://mlsanity.com/paper/2204.10377/) (2022)
- [Learning to Diversify for Single Domain Generalization](https://mlsanity.com/paper/2108.11726/) (2021)
- [The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning](https://mlsanity.com/paper/2505.15134/) (2025)
- [SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation](https://mlsanity.com/paper/2206.08367/) (2022)
- [Predicting with Confidence on Unseen Distributions](https://mlsanity.com/paper/2107.03315/) (2021)
- [AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation](https://mlsanity.com/paper/2106.04732/) (2021)
- [Robust Mean Teacher for Continual and Gradual Test-Time Adaptation](https://mlsanity.com/paper/2211.13081/) (2022)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Maximizing Confidence Alone Improves Reasoning](https://mlsanity.com/paper/2505.22660/) (2025)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Source-Free Domain Adaptation via Distribution Estimation](https://mlsanity.com/paper/2204.11257/) (2022)
- [Visual Prompt Tuning for Test-time Domain Adaptation](https://mlsanity.com/paper/2210.04831/) (2022)
- [Unsupervised Domain Adaptation of Object Detectors: A Survey](https://mlsanity.com/paper/2105.13502/) (2021)
- [Invariant Information Bottleneck for Domain Generalization](https://mlsanity.com/paper/2106.06333/) (2021)
- [Delving Deep into the Generalization of Vision Transformers under Distribution Shifts](https://mlsanity.com/paper/2106.07617/) (2021)
- [Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.16765/) (2021)
- [Self-Supervised Pretraining Improves Self-Supervised Pretraining](https://mlsanity.com/paper/2103.12718/) (2021)
- [TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2108.05988/) (2021)
- [Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation](https://mlsanity.com/paper/2107.05399/) (2021)
- [VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptation](https://mlsanity.com/paper/2103.14357/) (2021)
- [Mining Latent Classes for Few-shot Segmentation](https://mlsanity.com/paper/2103.15402/) (2021)
- [Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2104.09415/) (2021)
- [A Broad Study of Pre-training for Domain Generalization and Adaptation](https://mlsanity.com/paper/2203.11819/) (2022)
- [Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2303.03770/) (2023)
- [Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correction](https://mlsanity.com/paper/2306.00650/) (2023)
- [A Prototype-Oriented Framework for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2110.12024/) (2021)
- [PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization](https://mlsanity.com/paper/2307.15199/) (2023)
- [Source-Free Domain Adaptation with Frozen Multimodal Foundation Model](https://mlsanity.com/paper/2311.16510/) (2023)

## 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.