Hierarchical Consistency Learning for Test-Time Adaptation in Camouflage Perception
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 6860-6875
Abstract
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.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (U25A20535)
- National Natural Science Foundation of China (U23B2011)
- National Natural Science Foundation of China (62220106008)
- Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China (JYB2025XDXM102)
- National Key Research and Development Program of China (2025YFF0522500)
- Sichuan Science and Technology Program (2025YFNZH0034)
This publication has 72 references indexed in Scilit:
- COMPrompter: reconceptualized segment anything model with multiprompt network for camouflaged object detectionScience China Information Sciences, 2024
- FocusDiffuser: Perceiving Local Disparities for Camouflaged Object Detection2024
- TTT-MIM: Test-Time Training with Masked Image Modeling for Denoising Distribution Shifts2024
- Unlocking Attributes’ Contribution to Successful Camouflage: A Combined Textual and Visual Analysis Strategy2024
- CamoTeacher: Dual-Rotation Consistency Learning for Semi-supervised Camouflaged Object Detection2024
- Open-Vocabulary Camouflaged Object Segmentation2024
- Frequency-Spatial Entanglement Learning for Camouflaged Object Detection2024
- Just a Hint: Point-Supervised Camouflaged Object Detection2024
- PVT v2: Improved baselines with pyramid vision transformerComputational Visual Media, 2022
- MAS3K: An Open Dataset for Marine Animal Segmentation2021