Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings
This work provides an incremental improvement for researchers and practitioners working on unsupervised domain adaptation in semantic segmentation, specifically for synthetic-to-real scenarios.
This paper addresses the challenge of unsupervised domain adaptation in semantic segmentation, where models trained on labeled synthetic data are applied to unlabeled real-world data. The authors propose a feature clustering method combined with orthogonality and sparsity losses to regularize the feature space, achieving state-of-the-art performance in synthetic-to-real scenarios.
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.