Style Projected Clustering for Domain Generalized Semantic Segmentation

Citations Over TimeTop 10% of 2023 papers

Abstract

Existing semantic segmentation methods improve generalization capability, by regularizing various images to a canonical feature space. While this process contributes to generalization, it weakens the representation inevitably. In contrast to existing methods, we instead utilize the difference between images to build a better representation space, where the distinct style features are extracted and stored as the bases of representation. Then, the generalization to unseen image styles is achieved by projecting features to this known space. Specifically, we realize the style projection as a weighted combination of stored bases, where the similarity distances are adopted as the weighting factors. Based on the same concept, we extend this process to the decision part of model and promote the generalization of semantic prediction. By measuring the similarity distances to semantic bases (i.e., prototypes), we replace the common deterministic prediction with semantic clustering. Comprehensive experiments demonstrate the advantage of proposed method to the state of the art, up to 3.6% mIoU improvement in average on unseen scenarios. Code and models are available at https://gitee.com/mindspore/models/tree/master/research/cv/SPC-Net.

Related Papers

• → Extended implied weighting(2013)233 cited
• → Weighting in LCA – approaches and applications(2000)92 cited
• → The application of combination weighting approach in multiple attribute decision making(2009)9 cited
• → New Internet search volume-based weighting method for integrating various environmental impacts(2015)24 cited
• → A study of weighting factors of the quadratic performance index(1969)5 cited