Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation

Antoine Saporta, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 9072-9081

Abstract


In this work, we address the task of unsupervised domain adaptation (UDA) for semantic segmentation in presence of multiple target domains: the objective is to train a single model that can handle all these domains at test time. Such a multi-target adaptation is crucial for a variety of scenarios that real-world autonomous systems must handle. It is a challenging set-up since one faces not only the domain gap between the labeled source set and the unlabeled target set, but also the distribution shifts existing within the latter among the different target domains. To this end, we introduce two adversarial frameworks: (i) multi-discriminator, which explicitly aligns each target domain to its counterparts, and (ii) multi-target knowledge transfer, which learns a target-agnostic model thanks to a multi-teacher/single-student distillation mechanism. The evaluation is done on four newly proposed multi-target benchmarks for UDA in semantic segmentation. In all tested scenarios, our approaches consistently outperform baselines, setting competitive standards for the novel task.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Saporta_2021_ICCV, author = {Saporta, Antoine and Vu, Tuan-Hung and Cord, Matthieu and P\'erez, Patrick}, title = {Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {9072-9081} }