# Entropy Minimization vs. Diversity Maximization for Domain Adaptation

arXiv: https://arxiv.org/abs/2002.01690 · HTML: https://mlsanity.com/paper/2002.01690/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2020.

## Built on by (most cited first, 8 of 8)

- [A Prototype-Oriented Framework for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2110.12024/) (2021)
- [Source-Free Domain Adaptation for Image Segmentation](https://mlsanity.com/paper/2108.03152/) (2021)
- [Semantic Concentration for Domain Adaptation](https://mlsanity.com/paper/2108.05720/) (2021)
- [POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models](https://mlsanity.com/paper/2305.00350/) (2023)
- [Towards Better Selective Classification](https://mlsanity.com/paper/2206.09034/) (2022)
- [A Prototype-Oriented Clustering for Domain Shift with Source Privacy](https://mlsanity.com/paper/2302.03807/) (2023)
- [Bi-discriminator Domain Adversarial Neural Networks with Class-Level Gradient Alignment](https://mlsanity.com/paper/2310.13959/) (2023)
- [Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data](https://mlsanity.com/paper/2507.22488/) (2025)

## Abstract (arXiv)

Entropy minimization has been widely used in unsupervised domain adaptation (UDA). However, existing works reveal that entropy minimization only may result into collapsed trivial solutions. In this paper, we propose to avoid trivial solutions by further introducing diversity maximization. In order to achieve the possible minimum target risk for UDA, we show that diversity maximization should be elaborately balanced with entropy minimization, the degree of which can be finely controlled with the use of deep embedded validation in an unsupervised manner. The proposed minimal-entropy diversity maximization (MEDM) can be directly implemented by stochastic gradient descent without use of adversarial learning. Empirical evidence demonstrates that MEDM outperforms the state-of-the-art methods on four popular domain adaptation datasets.