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

Abstract

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.

Extension of our previous NeurIPS 2019 paper arXiv:1910.12181 on multi-source domain adaptation

References in corpus (9)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Learning Transferable Features with Deep Adaptation Networks
• Unsupervised Domain Adaptation with Residual Transfer Networks
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Domain Separation Networks
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• Wasserstein Distance Guided Representation Learning for Domain Adaptation
• Algorithms and Theory for Multiple-Source Adaptation
• Multi-source Domain Adaptation for Semantic Segmentation