Salvato in:
Dettagli Bibliografici
Autori principali: Guan, Juwei, Fang, Xiaolin, Kim, Donghyun, Gong, Haotian, Zhu, Tongxin, Ling, Zhen, Yang, Ming
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2503.22180
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913763714662400
author Guan, Juwei
Fang, Xiaolin
Kim, Donghyun
Gong, Haotian
Zhu, Tongxin
Ling, Zhen
Yang, Ming
author_facet Guan, Juwei
Fang, Xiaolin
Kim, Donghyun
Gong, Haotian
Zhu, Tongxin
Ling, Zhen
Yang, Ming
contents Low-quality data often suffer from insufficient image details, introducing an extra implicit aspect of camouflage that complicates camouflaged object detection (COD). Existing COD methods focus primarily on high-quality data, overlooking the challenges posed by low-quality data, which leads to significant performance degradation. Therefore, we propose KRNet, the first framework explicitly designed for COD on low-quality data. KRNet presents a Leader-Follower framework where the Leader extracts dual gold-standard distributions: conditional and hybrid, from high-quality data to drive the Follower in rectifying knowledge learned from low-quality data. The framework further benefits from a cross-consistency strategy that improves the rectification of these distributions and a time-dependent conditional encoder that enriches the distribution diversity. Extensive experiments on benchmark datasets demonstrate that KRNet outperforms state-of-the-art COD methods and super-resolution-assisted COD approaches, proving its effectiveness in tackling the challenges of low-quality data in COD.
format Preprint
id arxiv_https___arxiv_org_abs_2503_22180
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Knowledge Rectification for Camouflaged Object Detection: Unlocking Insights from Low-Quality Data
Guan, Juwei
Fang, Xiaolin
Kim, Donghyun
Gong, Haotian
Zhu, Tongxin
Ling, Zhen
Yang, Ming
Computer Vision and Pattern Recognition
Low-quality data often suffer from insufficient image details, introducing an extra implicit aspect of camouflage that complicates camouflaged object detection (COD). Existing COD methods focus primarily on high-quality data, overlooking the challenges posed by low-quality data, which leads to significant performance degradation. Therefore, we propose KRNet, the first framework explicitly designed for COD on low-quality data. KRNet presents a Leader-Follower framework where the Leader extracts dual gold-standard distributions: conditional and hybrid, from high-quality data to drive the Follower in rectifying knowledge learned from low-quality data. The framework further benefits from a cross-consistency strategy that improves the rectification of these distributions and a time-dependent conditional encoder that enriches the distribution diversity. Extensive experiments on benchmark datasets demonstrate that KRNet outperforms state-of-the-art COD methods and super-resolution-assisted COD approaches, proving its effectiveness in tackling the challenges of low-quality data in COD.
title Knowledge Rectification for Camouflaged Object Detection: Unlocking Insights from Low-Quality Data
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.22180