Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentation Article Swipe

MAKE IMPACT

Yuhang Zhang , Zhengyu Zhang , Muxin Liao , Shishun Tian , Wenbin Zou , Lu Zhang , Chen Xu · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2507.11955

Generalizable semantic segmentation aims to perform well on unseen target domains, a critical challenge due to real-world applications requiring high generalizability. Class-wise prototypes, representing class centroids, serve as domain-invariant cues that benefit generalization due to their stability and semantic consistency. However, this approach faces three challenges. First, existing methods often adopt coarse prototypical alignment strategies, which may hinder performance. Second, naive prototypes computed by averaging source batch features are prone to overfitting and may be negatively affected by unrelated source data. Third, most methods treat all source samples equally, ignoring the fact that different features have varying adaptation difficulties. To address these limitations, we propose a novel framework for generalizable semantic segmentation: Prototypical Progressive Alignment and Reweighting (PPAR), leveraging the strong generalization ability of the CLIP model. Specifically, we define two prototypes: the Original Text Prototype (OTP) and Visual Text Prototype (VTP), generated via CLIP to serve as a solid base for alignment. We then introduce a progressive alignment strategy that aligns features in an easy-to-difficult manner, reducing domain gaps gradually. Furthermore, we propose a prototypical reweighting mechanism that estimates the reliability of source data and adjusts its contribution, mitigating the effect of irrelevant or harmful features (i.e., reducing negative transfer). We also provide a theoretical analysis showing the alignment between our method and domain generalization theory. Extensive experiments across multiple benchmarks demonstrate that PPAR achieves state-of-the-art performance, validating its effectiveness.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2507.11955

PDF

https://arxiv.org/pdf/2507.11955

OA Status

green

OpenAlex ID

https://openalex.org/W4415141107

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4415141107

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2507.11955

Digital Object Identifier

Title

Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentation

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-07-16

Full publication date if available

Authors

Yuhang Zhang, Zhengyu Zhang, Muxin Liao, Shishun Tian, Wenbin Zou, Lu Zhang, Chen Xu

List of authors in order

Landing page

https://arxiv.org/abs/2507.11955

Publisher landing page

PDF URL

https://arxiv.org/pdf/2507.11955

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2507.11955

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload