Saved in:
Bibliographic Details
Main Authors: Zha, Mingfeng, Li, Tianyu, Wang, Guoqing, Pei, Yunqiang, Qiao, Chaofan, Zhang, Jiening, Yang, Yang, Shen, Heng Tao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.25651
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911715656990720
author Zha, Mingfeng
Li, Tianyu
Wang, Guoqing
Pei, Yunqiang
Qiao, Chaofan
Zhang, Jiening
Yang, Yang
Shen, Heng Tao
author_facet Zha, Mingfeng
Li, Tianyu
Wang, Guoqing
Pei, Yunqiang
Qiao, Chaofan
Zhang, Jiening
Yang, Yang
Shen, Heng Tao
contents Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes. Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and annotation dependency, limiting their adaptability to scene variations and unseen camouflage patterns. To overcome these, we propose the hierarchical consistency learning (HCL) framework, which integrates test-time adaptation for dynamic representation recalibration. Specifically, we design the hierarchical representation reconstruction (HRR) to alleviate feature entanglement by synergizing spatial reconstruction with dual-stream frequency-domain decomposition, enhancing robustness against appearance homogenization. The pixel and spectrum inference provide structural and contextual priors. We further introduce task affinity guidance (TAG) to propagate knowledge across branches via channel-wise affinity, aligning local discriminative cues and mitigating semantic drift. To ensure semantic invariance, we formulate the prototype consistency calibration (PCC), which aggregates region features into compact prototypes and establishes prototype-feature similarity. This imposes implicit and hierarchical constraints that bridge task and representation gaps. Extensive experiments across four camouflaged and four underwater object benchmarks, under three degradation settings, demonstrate that our method consistently outperforms state-of-the-art approaches, highlighting its robustness and generalization under distribution shifts.
format Preprint
id arxiv_https___arxiv_org_abs_2605_25651
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception
Zha, Mingfeng
Li, Tianyu
Wang, Guoqing
Pei, Yunqiang
Qiao, Chaofan
Zhang, Jiening
Yang, Yang
Shen, Heng Tao
Computer Vision and Pattern Recognition
Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes. Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and annotation dependency, limiting their adaptability to scene variations and unseen camouflage patterns. To overcome these, we propose the hierarchical consistency learning (HCL) framework, which integrates test-time adaptation for dynamic representation recalibration. Specifically, we design the hierarchical representation reconstruction (HRR) to alleviate feature entanglement by synergizing spatial reconstruction with dual-stream frequency-domain decomposition, enhancing robustness against appearance homogenization. The pixel and spectrum inference provide structural and contextual priors. We further introduce task affinity guidance (TAG) to propagate knowledge across branches via channel-wise affinity, aligning local discriminative cues and mitigating semantic drift. To ensure semantic invariance, we formulate the prototype consistency calibration (PCC), which aggregates region features into compact prototypes and establishes prototype-feature similarity. This imposes implicit and hierarchical constraints that bridge task and representation gaps. Extensive experiments across four camouflaged and four underwater object benchmarks, under three degradation settings, demonstrate that our method consistently outperforms state-of-the-art approaches, highlighting its robustness and generalization under distribution shifts.
title Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.25651