# MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation

arXiv: https://arxiv.org/abs/2003.00820 · HTML: https://mlsanity.com/paper/2003.00820/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2020.

## Built on by (most cited first, 20 of 20)

- [Invariant Information Bottleneck for Domain Generalization](https://mlsanity.com/paper/2106.06333/) (2021)
- [Pin the Memory: Learning to Generalize Semantic Segmentation](https://mlsanity.com/paper/2204.03609/) (2022)
- [Affective Image Content Analysis: Two Decades Review and New Perspectives](https://mlsanity.com/paper/2106.16125/) (2021)
- [Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain](https://mlsanity.com/paper/2202.10725/) (2022)
- [Domain-Specific Bias Filtering for Single Labeled Domain Generalization](https://mlsanity.com/paper/2110.00726/) (2021)
- [Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training](https://mlsanity.com/paper/2405.02954/) (2024)
- [Latent Covariate Shift: Unlocking Partial Identifiability for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2208.14161/) (2022)
- [Subject-Based Domain Adaptation for Facial Expression Recognition](https://mlsanity.com/paper/2312.05632/) (2023)
- [More is Better: Deep Domain Adaptation with Multiple Sources](https://mlsanity.com/paper/2405.00749/) (2024)
- [Multi-source Domain Adaptation for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2408.16469/) (2024)
- [Mixture Domain Adaptation to Improve Semantic Segmentation in Real-World Surveillance](https://mlsanity.com/paper/2211.10119/) (2022)
- [Uncertainty-Aware Pseudo-Label Filtering for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2403.11256/) (2024)
- [Learning to Generalize over Subpartitions for Heterogeneity-aware Domain Adaptive Nuclei Segmentation](https://mlsanity.com/paper/2401.09496/) (2024)
- [Progressive Multi-Source Domain Adaptation for Personalized Facial Expression Recognition](https://mlsanity.com/paper/2504.04252/) (2025)
- [A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning](https://mlsanity.com/paper/2502.04242/) (2025)
- [Improving Transferability of Domain Adaptation Networks Through Domain Alignment Layers](https://mlsanity.com/paper/2109.02693/) (2021)
- [MuSACo: Multimodal Subject-Specific Selection and Adaptation for Expression Recognition with Co-Training](https://mlsanity.com/paper/2508.12522/) (2025)
- [AWADA: Attention-Weighted Adversarial Domain Adaptation for Object Detection](https://mlsanity.com/paper/2208.14662/) (2022)
- [Let Synthetic Data Shine: Domain Reassembly and Soft-Fusion for Single Domain Generalization](https://mlsanity.com/paper/2503.13617/) (2025)
- [Unified Optimization of Source Weights and Transfer Quantities in Multi-Source Transfer Learning: An Asymptotic Framework](https://mlsanity.com/paper/2601.10779/) (2026)

## Abstract (arXiv)

Domain adaptation aims to learn a transferable model to bridge the domain shift between one labeled source domain and another sparsely labeled or unlabeled target domain. Since the labeled data may be collected from multiple sources, multi-source domain adaptation (MDA) has attracted increasing attention. Recent MDA methods do not consider the pixel-level alignment between sources and target or the misalignment across different sources. In this paper, we propose a novel MDA framework to address these challenges. Specifically, we design an end-to-end Multi-source Adversarial Domain Aggregation Network (MADAN). First, an adapted domain is generated for each source with dynamic semantic consistency while aligning towards the target at the pixel-level cycle-consistently. Second, sub-domain aggregation discriminator and cross-domain cycle discriminator are proposed to make different adapted domains more closely aggregated. Finally, feature-level alignment is performed between the aggregated domain and the target domain while training the task network. For the segmentation adaptation, we further enforce category-level alignment and incorporate context-aware generation, which constitutes MADAN+. We conduct extensive MDA experiments on digit recognition, object classification, and simulation-to-real semantic segmentation. The results demonstrate that the proposed MADAN and MANDA+ models outperform state-of-the-art approaches by a large margin.