Inter- and Intra-image Refinement for Few Shot Segmentation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Fu, Ourui, He, Hangzhou, Li, Kaiwen, Zhang, Xinliang, Zhu, Lei, Zeng, Shuang, Xie, Zhaoheng, Lu, Yanye
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911321238274048
author Fu, Ourui
He, Hangzhou
Li, Kaiwen
Zhang, Xinliang
Zhu, Lei
Zeng, Shuang
Xie, Zhaoheng
Lu, Yanye
author_facet Fu, Ourui
He, Hangzhou
Li, Kaiwen
Zhang, Xinliang
Zhu, Lei
Zeng, Shuang
Xie, Zhaoheng
Lu, Yanye
contents Deep neural networks for semantic segmentation rely on large-scale annotated datasets, leading to an annotation bottleneck that motivates few shot semantic segmentation (FSS) which aims to generalize to novel classes with minimal labeled exemplars. Most existing FSS methods adopt a prototype-based paradigm, which generates query prior map by extracting masked-area features from support images and then makes predictions guided by the prior map. However, they suffer from two critical limitations induced by inter- and intra-image discrepancies: 1) The intra-class gap between support and query images, caused by single-prototype representation, results in scattered and noisy prior maps; 2) The inter-class interference from visually similar but semantically distinct regions leads to inconsistent support-query feature matching and erroneous predictions. To address these issues, we propose the Inter- and Intra-image Refinement (IIR) model. The model contains an inter-image class activation mapping based method that generates two prototypes for class-consistent region matching, including core discriminative features and local specific features, and yields an accurate and robust prior map. For intra-image refinement, a directional dropout mechanism is introduced to mask inconsistent support-query feature pairs in cross attention, thereby enhancing decoder performance. Extensive experiments demonstrate that IIR achieves state-of-the-art performance on 9 benchmarks, covering standard FSS, part FSS, and cross-domain FSS. Our source code is available at \href{https://github.com/forypipi/IIR}{https://github.com/forypipi/IIR}.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05838
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Inter- and Intra-image Refinement for Few Shot Segmentation
Fu, Ourui
He, Hangzhou
Li, Kaiwen
Zhang, Xinliang
Zhu, Lei
Zeng, Shuang
Xie, Zhaoheng
Lu, Yanye
Computer Vision and Pattern Recognition
Deep neural networks for semantic segmentation rely on large-scale annotated datasets, leading to an annotation bottleneck that motivates few shot semantic segmentation (FSS) which aims to generalize to novel classes with minimal labeled exemplars. Most existing FSS methods adopt a prototype-based paradigm, which generates query prior map by extracting masked-area features from support images and then makes predictions guided by the prior map. However, they suffer from two critical limitations induced by inter- and intra-image discrepancies: 1) The intra-class gap between support and query images, caused by single-prototype representation, results in scattered and noisy prior maps; 2) The inter-class interference from visually similar but semantically distinct regions leads to inconsistent support-query feature matching and erroneous predictions. To address these issues, we propose the Inter- and Intra-image Refinement (IIR) model. The model contains an inter-image class activation mapping based method that generates two prototypes for class-consistent region matching, including core discriminative features and local specific features, and yields an accurate and robust prior map. For intra-image refinement, a directional dropout mechanism is introduced to mask inconsistent support-query feature pairs in cross attention, thereby enhancing decoder performance. Extensive experiments demonstrate that IIR achieves state-of-the-art performance on 9 benchmarks, covering standard FSS, part FSS, and cross-domain FSS. Our source code is available at \href{https://github.com/forypipi/IIR}{https://github.com/forypipi/IIR}.
title Inter- and Intra-image Refinement for Few Shot Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.05838