# Maximum Density Divergence for Domain Adaptation

arXiv: https://arxiv.org/abs/2004.12615 · HTML: https://mlsanity.com/paper/2004.12615/

## Key facts

- Cited by 76 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2020.

## Built on by (most cited first, 30 of 76)

- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.04151/) (2021)
- [Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2204.00570/) (2022)
- [AD-CLIP: Adapting Domains in Prompt Space Using CLIP](https://mlsanity.com/paper/2308.05659/) (2023)
- [ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation](https://mlsanity.com/paper/2306.04344/) (2023)
- [Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective](https://mlsanity.com/paper/2303.13434/) (2023)
- [Test-time Batch Statistics Calibration for Covariate Shift](https://mlsanity.com/paper/2110.04065/) (2021)
- [StyLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-based Domain Generalization](https://mlsanity.com/paper/2302.09251/) (2023)
- [ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation](https://mlsanity.com/paper/2205.14566/) (2022)
- [Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2403.02899/) (2024)
- [Domain Adaptive Semantic Segmentation without Source Data](https://mlsanity.com/paper/2110.06484/) (2021)
- [Self-Adversarial Disentangling for Specific Domain Adaptation](https://mlsanity.com/paper/2108.03553/) (2021)
- [Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation](https://mlsanity.com/paper/2109.04015/) (2021)
- [Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain](https://mlsanity.com/paper/2202.10725/) (2022)
- [Conditional Bures Metric for Domain Adaptation](https://mlsanity.com/paper/2108.00302/) (2021)
- [APPLeNet: Visual Attention Parameterized Prompt Learning for Few-Shot Remote Sensing Image Generalization using CLIP](https://mlsanity.com/paper/2304.05995/) (2023)
- [SPA: A Graph Spectral Alignment Perspective for Domain Adaptation](https://mlsanity.com/paper/2310.17594/) (2023)
- [First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains](https://mlsanity.com/paper/2211.11719/) (2022)
- [Unknown Prompt, the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalization](https://mlsanity.com/paper/2404.00710/) (2024)
- [ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery](https://mlsanity.com/paper/2504.03755/) (2025)
- [AADG: Automatic Augmentation for Domain Generalization on Retinal Image Segmentation](https://mlsanity.com/paper/2207.13249/) (2022)
- [Variational Model Perturbation for Source-Free Domain Adaptation](https://mlsanity.com/paper/2210.10378/) (2022)
- [An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detection](https://mlsanity.com/paper/2204.00154/) (2022)
- [Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance](https://mlsanity.com/paper/2110.06893/) (2021)
- [Handling Out-of-Distribution Data: A Survey](https://mlsanity.com/paper/2507.21160/) (2025)
- [Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2403.06946/) (2024)
- [CDAD-Net: Bridging Domain Gaps in Generalized Category Discovery](https://mlsanity.com/paper/2404.05366/) (2024)
- [I2V-GAN: Unpaired Infrared-to-Visible Video Translation](https://mlsanity.com/paper/2108.00913/) (2021)
- [Better Pseudo-label: Joint Domain-aware Label and Dual-classifier for Semi-supervised Domain Generalization](https://mlsanity.com/paper/2110.04820/) (2021)
- [Gradient Harmonization in Unsupervised Domain Adaptation](https://mlsanity.com/paper/2408.00288/) (2024)

## Abstract (arXiv)

Unsupervised domain adaptation addresses the problem of transferring knowledge from a well-labeled source domain to an unlabeled target domain where the two domains have distinctive data distributions. Thus, the essence of domain adaptation is to mitigate the distribution divergence between the two domains. The state-of-the-art methods practice this very idea by either conducting adversarial training or minimizing a metric which defines the distribution gaps. In this paper, we propose a new domain adaptation method named Adversarial Tight Match (ATM) which enjoys the benefits of both adversarial training and metric learning. Specifically, at first, we propose a novel distance loss, named Maximum Density Divergence (MDD), to quantify the distribution divergence. MDD minimizes the inter-domain divergence ("match" in ATM) and maximizes the intra-class density ("tight" in ATM). Then, to address the equilibrium challenge issue in adversarial domain adaptation, we consider leveraging the proposed MDD into adversarial domain adaptation framework. At last, we tailor the proposed MDD as a practical learning loss and report our ATM. Both empirical evaluation and theoretical analysis are reported to verify the effectiveness of the proposed method. The experimental results on four benchmarks, both classical and large-scale, show that our method is able to achieve new state-of-the-art performance on most evaluations. Codes and datasets used in this paper are available at it github.com/lijin118/ATM.