Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings

Marco Toldo, Umberto Michieli, Pietro Zanuttigh; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021, pp. 1358-1368

Abstract


Deep learning frameworks allowed for a remarkable advancement in semantic segmentation, but the data hungry nature of convolutional networks has rapidly raised the demand for adaptation techniques able to transfer learned knowledge from label-abundant domains to unlabeled ones. In this paper we propose an effective Unsupervised Domain Adaptation (UDA) strategy, based on a feature clustering method that captures the different semantic modes of the feature distribution and groups features of the same class into tight and well-separated clusters. Furthermore, we introduce two novel learning objectives to enhance the discriminative clustering performance: an orthogonality loss forces spaced out individual representations to be orthogonal, while a sparsity loss reduces class-wise the number of active feature channels. The joint effect of these modules is to regularize the structure of the feature space. Extensive evaluations in the synthetic-to-real scenario show that we achieve state-of-the-art performance.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Toldo_2021_WACV, author = {Toldo, Marco and Michieli, Umberto and Zanuttigh, Pietro}, title = {Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2021}, pages = {1358-1368} }