Pixel’s Neighbors Are Noteworthy: Localized Vision–Language Attention for Remote Sensing Semantic Segmentation

In recent years, vision–language models (VLMs) have been introduced into remote sensing semantic segmentation to provide richer semantic representations through visual–textual alignment. However, most existing VLM-based segmentation methods focus on global semantic alignment while neglecting pixel-l...

Descrizione completa

Dettagli Bibliografici

Autori principali:	Cheng Zeng, Sheng Tao, Xiaowei Tan, Zhifeng Xiao, Lei Hu
Natura:	Artigo
Lingua:	Inglês
Pubblicazione:	MDPI AG 2026-05-01
Serie:	Remote Sensing
Soggetti:	remote sensing semantic segmentation vision–language model Vision Transformer neighborhood attention RemoteCLIP
Accesso online:	https://www.mdpi.com/2072-4292/18/11/1708
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!