Lune

CVPR2023Top-tier venue

Style Projected Clustering for Domain Generalized Semantic Segmentation

Wei Huang, Chang Chen, Yong Li, Jiacheng Li, Cheng Li, Fenglong Song, Youliang Yan, Zhiwei Xiong

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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

24 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Learning Frequency-Adapted Vision Foundation Model for Domain Generalized Semantic Segmentation cites Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation
  • Learning Frequency-Adapted Vision Foundation Model for Domain Generalized Semantic Segmentation cites Learning Generalized Segmentation for Foggy-Scenes by Bi-directional Wavelet Guidance
  • Learning Frequency-Adapted Vision Foundation Model for Domain Generalized Semantic Segmentation cites Learning Content-Enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation
  • Domain Generalization with MixStyle cites Episodic Training for Domain Generalization
  • Learning Generalized Segmentation for Foggy-Scenes by Bi-directional Wavelet Guidance cites Learning Content-Enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation
  • Learning Spectral-Decomposited Tokens for Domain Generalized Semantic Segmentation cites Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation
  • Learning Spectral-Decomposited Tokens for Domain Generalized Semantic Segmentation cites Learning Generalized Segmentation for Foggy-Scenes by Bi-directional Wavelet Guidance
  • Learning Spectral-Decomposited Tokens for Domain Generalized Semantic Segmentation cites Learning Content-Enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers24

  1. Learning Content-Enhanced Mask Transformer for Domain Generalized Urban-Scene SegmentationQi Bi, Shaodi You, Theo GeversAAAI 2024 · 77 citations
  2. Learning Frequency-Adapted Vision Foundation Model for Domain Generalized Semantic SegmentationQi Bi, Jingjun Yi, Hao Zheng, Haolan Zhan et al.NeurIPS 2024 · 62 citations
  3. Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic SegmentationZhixiang Wei, Lin Chen, Yi Jin, Xiaoxiao Ma et al.CVPR 2024 · 61 citations
  4. Learning Generalized Segmentation for Foggy-Scenes by Bi-directional Wavelet GuidanceQi Bi, Shaodi You, Theo GeversAAAI 2024 · 45 citations
  5. Learning Spectral-Decomposited Tokens for Domain Generalized Semantic SegmentationJingjun Yi, Qi Bi, Hao Zheng, Haolan Zhan et al.ACM MM 2024 · 25 citations

Builds on27

  1. PANet: Few-Shot Image Semantic Segmentation With Prototype AlignmentKaixin Wang, Jun Hao Liew, Yingtian Zou, Daquan Zhou et al.ICCV 2019 · 1,404 citations
  2. Domain Generalization with MixStyleKaiyang Zhou, Yongxin Yang, Yu Qiao, Tao XiangICLR 2021 · 986 citations
  3. Exploring Cross-Image Pixel Contrast for Semantic SegmentationWenguan Wang, Tianfei Zhou, Fisher Yu, Jifeng Dai et al.ICCV 2021 · 568 citations
  4. Episodic Training for Domain GeneralizationDa Li, Jianshu Zhang, Yongxin Yang, Cong Liu et al.ICCV 2019 · 488 citations
  5. Prototypical Contrastive Learning of Unsupervised RepresentationsJunnan Li, Pan Zhou, Caiming Xiong, Steven C. H. HoiICLR 2021 · 484 citations

Related papers

  1. WildNet: Learning Domain Generalized Semantic Segmentation from the WildSuhyeon Lee, Hongje Seong, Seongwon Lee, Euntai KimCVPR 2022 · 95 citations
  2. Collaborating Foundation Models for Domain Generalized Semantic SegmentationYasser Benigmim, Subhankar Roy, Slim Essid, Vicky Kalogeiton et al.CVPR 2024
  3. Exploring Semantic Consistency and Style Diversity for Domain Generalized Semantic SegmentationHongwei Niu, Linhuang Xie, Jianghang Lin, Shengchuan ZhangAAAI 2025 · 16 citations
  4. Adversarial Style Augmentation for Domain Generalized Urban-Scene SegmentationZhun Zhong, Yuyang Zhao, Gim Hee Lee, Nicu SebeNeurIPS 2022 · 130 citations
  5. Generalized Semantic Segmentation by Self-Supervised Source Domain Projection and Multi-Level Contrastive LearningLiwei Yang, Xiang Gu, Jian SunAAAI 2023 · 25 citations
Dusk over the sea between two cliffs drawn in fine vertical lines