Enhancing Few-Shot Out-of-Distribution Detection via the Refinement of Foreground and Background

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Tianyu, Wu, Zongqian, Cai, Songyue, Hu, Ping, Zhu, Xiaofeng
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915999591170048
author Li, Tianyu
Wu, Zongqian
Cai, Songyue
Hu, Ping
Zhu, Xiaofeng
author_facet Li, Tianyu
Wu, Zongqian
Cai, Songyue
Hu, Ping
Zhu, Xiaofeng
contents CLIP-based foreground-background (FG-BG) decomposition methods have demonstrated remarkable effectiveness in improving few-shot out-of-distribution (OOD) detection performance. However, existing approaches still suffer from several limitations. For background regions obtained from decomposition, existing methods adopt a uniform suppression strategy for all patches, overlooking the varying contributions of different patches to the prediction. For foreground regions, existing methods fail to adequately consider that some local patches may exhibit appearance or semantic similarity to other classes, which may mislead the training process. To address these issues, we propose a new plug-and-play framework. This framework consists of three core components: (1) a Foreground-Background Decomposition module, which follows previous FG-BG methods to separate an image into foreground and background regions; (2) an Adaptive Background Suppression module, which adaptively weights patch classification entropy; and (3) a Confusable Foreground Rectification module, which identifies and rectifies confusable foreground patches. Extensive experimental results demonstrate that the proposed plug-and-play framework significantly improves the performance of existing FG-BG decomposition methods. Code is available at: https://github.com/lounwb/FoBoR.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15065
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Enhancing Few-Shot Out-of-Distribution Detection via the Refinement of Foreground and Background
Li, Tianyu
Wu, Zongqian
Cai, Songyue
Hu, Ping
Zhu, Xiaofeng
Computer Vision and Pattern Recognition
CLIP-based foreground-background (FG-BG) decomposition methods have demonstrated remarkable effectiveness in improving few-shot out-of-distribution (OOD) detection performance. However, existing approaches still suffer from several limitations. For background regions obtained from decomposition, existing methods adopt a uniform suppression strategy for all patches, overlooking the varying contributions of different patches to the prediction. For foreground regions, existing methods fail to adequately consider that some local patches may exhibit appearance or semantic similarity to other classes, which may mislead the training process. To address these issues, we propose a new plug-and-play framework. This framework consists of three core components: (1) a Foreground-Background Decomposition module, which follows previous FG-BG methods to separate an image into foreground and background regions; (2) an Adaptive Background Suppression module, which adaptively weights patch classification entropy; and (3) a Confusable Foreground Rectification module, which identifies and rectifies confusable foreground patches. Extensive experimental results demonstrate that the proposed plug-and-play framework significantly improves the performance of existing FG-BG decomposition methods. Code is available at: https://github.com/lounwb/FoBoR.
title Enhancing Few-Shot Out-of-Distribution Detection via the Refinement of Foreground and Background
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.15065