FS-SegDiff: Mitigating Intra-Class Variation and Attention Leakage for Robust Diffusion-Based Few-Shot Semantic Segmentation

Few-shot semantic segmentation (FSS) has gained a significant attention as a promising solution to segmenting the target objects of unseen classes using only a few annotated examples. Recently, pretrained diffusion models have emerged as an effective approach for FSS, acting as both a powerful featu...

Deskribapen osoa

Xehetasun bibliografikoak

Egile Nagusiak:	Jaehyun Kim, Wonyong Seo, Munchurl Kim
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	IEEE 2026-01-01
Saila:	IEEE Access
Gaiak:	Attention leakage diffusion diffusion-based few-shot semantic segmentation few-shot semantic segmentation multi-scale feature matching
Sarrera elektronikoa:	https://ieeexplore.ieee.org/document/11357902/
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!