Structure Enhancement and Cross-Modal Alignment for Open-Vocabulary Semantic Segmentation
Journal of Computing and Electronic Information Management · 29.04.2026 · 21 (1) · 111-117
DOI: 10.54097/6kbbz575 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computing and Electronic Information Management, online erschienen am 29.04.2026. Verfasst von Jiawei Bai. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
This paper proposes a structure-enhanced cross-modal alignment method for open-vocabulary semantic segmentation. Existing methods mostly rely on CLIP’s image-level vision-language alignment capability, but CLIP visual features remain insufficient for modeling fine-grained spatial information such as boundaries, textures, and region structures. Moreover, relying solely on semantic alignment between images and text categories makes it difficult to model fine-grained correspondences between visual and textual information. To address these issues, we design a DINO Structure Enhancement Module and a Cross-Modal Alignment Module (CCMA). The DINO Structure Enhancement Module introduces a parameter-frozen DINO model to extract structural priors and adaptively enhance CLIP visual features, thereby producing structure-aware visual features. CCMA jointly models global visual semantics, local region features, and text semantic prototypes to mine fine-grained vision-language consistency at the region level, thereby strengthening the correspondence between image regions and textual semantics. Experimental results demonstrate that the proposed method effectively improves open-vocabulary semantic segmentation performance.
Zitieren
APA
Bai, J. (2026). Structure Enhancement and Cross-Modal Alignment for Open-Vocabulary Semantic Segmentation. Journal of Computing and Electronic Information Management, 21(1), 111-117. https://doi.org/10.54097/6kbbz575
Vancouver
Bai J. Structure Enhancement and Cross-Modal Alignment for Open-Vocabulary Semantic Segmentation. Journal of Computing and Electronic Information Management. 2026;21(1):111-117. doi:10.54097/6kbbz575
BibTeX
@article{Bai2026,
author = {Bai, Jiawei},
title = {Structure Enhancement and Cross-Modal Alignment for Open-Vocabulary Semantic Segmentation},
journal = {Journal of Computing and Electronic Information Management},
year = {2026},
volume = {21},
number = {1},
pages = {111--117},
doi = {10.54097/6kbbz575}
}
EUVIMED