pith. sign in

arxiv: 2605.25651 · v1 · pith:RSDVFN3Jnew · submitted 2026-05-25 · 💻 cs.CV

Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception

Mingfeng Zha , Tianyu Li , Guoqing Wang , Yunqiang Pei , Chaofan Qiao , Jiening Zhang , Yang Yang , Heng Tao Shen This is my paper

Pith reviewed 2026-06-29 22:22 UTC · model grok-4.3

classification 💻 cs.CV
keywords camouflaged object detectiontest-time adaptationhierarchical consistency learningdomain shiftunderwater object detectionrepresentation recalibrationconsistency constraints
0
0 comments X

The pith

Hierarchical consistency learning framework adapts camouflaged object detectors at test time using unlabeled data.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes the hierarchical consistency learning framework to overcome the limitations of static trained models in camouflaged object detection. It introduces three components that work together at inference time: hierarchical representation reconstruction to separate spatial and frequency features, task affinity guidance to align information across processing branches, and prototype consistency calibration to keep semantic meanings stable. These allow the model to recalibrate its internal representations when facing new scenes or camouflage styles without needing fresh labels. Experiments across eight benchmarks under multiple degradation conditions show the approach beats prior methods. A reader would care because real-world camouflage perception often encounters distribution shifts that break fixed models.

Core claim

The hierarchical consistency learning (HCL) framework integrates hierarchical representation reconstruction (HRR) to disentangle features via spatial and dual-stream frequency decomposition, task affinity guidance (TAG) to propagate knowledge through channel-wise affinity, and prototype consistency calibration (PCC) to aggregate region features into prototypes and enforce similarity constraints, enabling dynamic recalibration of representations at test time for robustness under distribution shifts.

What carries the argument

Hierarchical consistency learning (HCL) framework combining hierarchical representation reconstruction, task affinity guidance, and prototype consistency calibration to enforce spatial, spectral, affinity, and prototype-level constraints during test-time adaptation.

If this is right

  • The method reduces dependence on annotated data when deploying detectors in new environments.
  • It maintains performance across camouflaged and underwater tasks under appearance changes and degradations.
  • The consistency constraints bridge gaps between different processing branches and representation levels.
  • Generalization improves without retraining when encountering unseen camouflage patterns.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Similar hierarchical consistency ideas could be tested on other detection tasks that face domain shifts, such as medical lesion detection or aerial object recognition.
  • The frequency-domain decomposition step might be replaced with other signal-processing priors to check if the gains persist.
  • Extending the prototype calibration to video inputs could reveal whether temporal consistency emerges as an additional benefit.

Load-bearing premise

The proposed components can dynamically recalibrate representations at test time using only unlabeled data and internal consistency constraints without introducing semantic drift or requiring task-specific tuning.

What would settle it

An experiment on one of the eight benchmarks where applying the full HCL adaptation lowers detection performance relative to the non-adapted baseline model or produces visibly mismatched prototypes between source and target domains.

Figures

Figures reproduced from arXiv: 2605.25651 by Chaofan Qiao, Guoqing Wang, Heng Tao Shen, Jiening Zhang, Mingfeng Zha, Tianyu Li, Yang Yang, Yunqiang Pei.

Figure 1
Figure 1. Figure 1: (a) Traditional methods follow the train-fix-test paradigm (top), while our method adopts the train-adapt-test paradigm to dynamically perceive the scene (bottom). (b) Three testing sample degradation strategies (top) and qualitative comparisons (bottom). (c) Left: Performance drop ∆Sm of comparison methods, relative to our method. Right: Performance variation (F w β and Em on the NC4K) before (solid marke… view at source ↗
Figure 2
Figure 2. Figure 2: Stage 1: The input image undergoes masked patch partitioning in the spatial domain, while threshold-based masking is applied to obtain high- and [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Qualitative comparison on normal scenarios. Best viewed by zooming in. [PITH_FULL_IMAGE:figures/full_fig_p009_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Qualitative comparison on degraded camouflaged scenarios. (a)-(c): GN setting, (d)-(f): GB setting, (g)-(i): CR setting. [PITH_FULL_IMAGE:figures/full_fig_p010_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative ablation of the proposed components. Variants corresponding to Table [PITH_FULL_IMAGE:figures/full_fig_p010_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Quantitative ablation on the ratios of spatial, low-frequency, and high-frequency masks (with optimal spatial ratio), as well as the effects of Top-K [PITH_FULL_IMAGE:figures/full_fig_p011_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Qualitative comparison on degraded underwater scenarios. (a)-(c): GN setting, (d)-(f): GB setting, (g)-(i): CR setting. [PITH_FULL_IMAGE:figures/full_fig_p013_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Failure cases under degradation conditions. [PITH_FULL_IMAGE:figures/full_fig_p013_8.png] view at source ↗
read the original 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.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The manuscript proposes the Hierarchical Consistency Learning (HCL) framework for test-time adaptation in camouflaged object detection. It integrates three modules: hierarchical representation reconstruction (HRR) that combines spatial reconstruction with dual-stream frequency-domain decomposition to reduce feature entanglement, task affinity guidance (TAG) that propagates knowledge across branches using channel-wise affinity to align discriminative cues, and prototype consistency calibration (PCC) that aggregates region features into prototypes and enforces prototype-feature similarity to maintain semantic invariance. The central claim is that this enables dynamic recalibration at test time using only unlabeled data and outperforms state-of-the-art methods across four camouflaged and four underwater benchmarks under three degradation settings.

Significance. If the experimental outperformance holds with proper ablations and metrics, the work would advance test-time adaptation for perception under distribution shifts in visually challenging domains. The consistency-based approach without task-specific tuning addresses a practical limitation of static COD models.

major comments (1)
  1. [Abstract] Abstract: the central claim of consistent outperformance over SOTA is stated without any quantitative results, error bars, ablation tables, or specific metrics (e.g., mIoU or F-measure deltas), preventing verification that the HRR/TAG/PCC modules deliver the claimed robustness.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the detailed review and constructive comment on the abstract. We address the point below and will revise the manuscript accordingly.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claim of consistent outperformance over SOTA is stated without any quantitative results, error bars, ablation tables, or specific metrics (e.g., mIoU or F-measure deltas), preventing verification that the HRR/TAG/PCC modules deliver the claimed robustness.

    Authors: We agree that the abstract would benefit from explicit quantitative support for the outperformance claim. The full manuscript already contains detailed tables with mIoU, F-measure, and other metrics across all benchmarks and degradation settings, plus ablations isolating HRR, TAG, and PCC contributions. In the revised version we will add concise numerical highlights to the abstract (e.g., average mIoU gains and F-measure deltas versus the strongest baselines) so that the central claim can be verified at a glance while remaining within length limits. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The provided abstract and context describe a framework (HCL) with three modules (HRR, TAG, PCC) motivated by distinct goals such as alleviating feature entanglement, propagating knowledge, and ensuring semantic invariance. No equations, fitted parameters, self-citations, or derivations are shown that reduce any claimed prediction or result to its inputs by construction. The central claims rest on experimental outperformance under distribution shifts, which is independent of the module definitions themselves. This is a standard non-finding for a methods paper whose derivation chain does not exhibit the enumerated circular patterns.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review yields no explicit free parameters, axioms, or invented entities; the proposal relies on standard deep learning assumptions about feature consistency and affinity without detailing any fitted values or new postulated constructs.

pith-pipeline@v0.9.1-grok · 5756 in / 1176 out tokens · 31587 ms · 2026-06-29T22:22:04.267109+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

85 extracted references · 9 canonical work pages · 2 internal anchors

  1. [1]

    Pranet: Parallel reverse attention network for polyp segmentation,

    D.-P. Fan, G.-P. Ji, T. Zhou, G. Chen, H. Fu, J. Shen, and L. Shao, “Pranet: Parallel reverse attention network for polyp segmentation,” in International conference on medical image computing and computer- assisted intervention. Springer, 2020, pp. 263–273

    2020

  2. [2]

    Test- time training with self-supervision for generalization under distribution shifts,

    Y . Sun, X. Wang, Z. Liu, J. Miller, A. Efros, and M. Hardt, “Test- time training with self-supervision for generalization under distribution shifts,” inInternational conference on machine learning. PMLR, 2020, pp. 9229–9248

    2020

  3. [3]

    Ef- ficient test-time model adaptation without forgetting,

    S. Niu, J. Wu, Y . Zhang, Y . Chen, S. Zheng, P. Zhao, and M. Tan, “Ef- ficient test-time model adaptation without forgetting,” inInternational conference on machine learning. PMLR, 2022, pp. 16 888–16 905

    2022

  4. [4]

    Dual domain perception and progressive refinement for mirror detection,

    M. Zha, F. Fu, Y . Pei, G. Wang, T. Li, X. Tang, Y . Yang, and H. T. Shen, “Dual domain perception and progressive refinement for mirror detection,”IEEE Transactions on Circuits and Systems for Video Technology, vol. 34, no. 11, pp. 11 942–11 953, 2024

    2024

  5. [5]

    Heterogeneous experts and hierarchical perception for underwa- ter salient object detection,

    M. Zha, G. Wang, Y . Pei, T. Li, X. Tang, C. Li, Y . Yang, and H. T. Shen, “Heterogeneous experts and hierarchical perception for underwa- ter salient object detection,”IEEE Transactions on Image Processing, 2025

    2025

  6. [6]

    Weakly-supervised mirror detection via scribble annotations,

    M. Zha, Y . Pei, G. Wang, T. Li, Y . Yang, W. Qian, and H. T. Shen, “Weakly-supervised mirror detection via scribble annotations,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 7, 2024, pp. 6953–6961

    2024

  7. [7]

    Distortion- aware transformer in 360 salient object detection,

    Y . Zhao, L. Zhao, Q. Yu, L. Sheng, J. Zhang, and D. Xu, “Distortion- aware transformer in 360 salient object detection,” inProceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 499–508

    2023

  8. [8]

    Seeing beyond illusion: Generalized and efficient mirror detection,

    M. Zha, G. Wang, T. Li, W. Dong, P. Wang, and Y . Yang, “Seeing beyond illusion: Generalized and efficient mirror detection,” inProceedings of the AAAI Conference on Artificial Intelligence, 2026

    2026

  9. [9]

    Language- guided salient object ranking,

    F. Liu, Y . Liu, K. Xu, S. Ye, G. P. Hancke, and R. W. Lau, “Language- guided salient object ranking,” inProceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 29 803–29 813

    2025

  10. [10]

    A contrastive-learning framework for unsupervised salient object detection,

    H. Guan, J. Lin, and R. W. Lau, “A contrastive-learning framework for unsupervised salient object detection,”IEEE Transactions on Image Processing, 2025

    2025

  11. [11]

    arXiv preprint arXiv:2207.00794 (2022)

    Y . Sun, S. Wang, C. Chen, and T.-Z. Xiang, “Boundary-guided camou- flaged object detection,”arXiv preprint arXiv:2207.00794, 2022

    work page arXiv 2022

  12. [12]

    Inferring camouflaged objects by texture-aware interactive guidance network,

    J. Zhu, X. Zhang, S. Zhang, and J. Liu, “Inferring camouflaged objects by texture-aware interactive guidance network,” inProceedings of the AAAI conference on artificial intelligence, vol. 35, no. 4, 2021, pp. 3599– 3607

    2021

  13. [13]

    Frequency-spatial entanglement learning for camouflaged object detection,

    Y . Sun, C. Xu, J. Yang, H. Xuan, and L. Luo, “Frequency-spatial entanglement learning for camouflaged object detection,” inEuropean Conference on Computer Vision. Springer, 2024, pp. 343–360

    2024

  14. [14]

    Source-free depth for object pop-out,

    Z. Wu, D. P. Paudel, D.-P. Fan, J. Wang, S. Wang, C. Demonceaux, R. Timofte, and L. Van Gool, “Source-free depth for object pop-out,” inProceedings of the IEEE/CVF international conference on computer vision, 2023, pp. 1032–1042

    2023

  15. [15]

    Predictive uncer- tainty estimation for camouflaged object detection,

    Y . Zhang, J. Zhang, W. Hamidouche, and O. Deforges, “Predictive uncer- tainty estimation for camouflaged object detection,”IEEE Transactions on Image Processing, vol. 32, pp. 3580–3591, 2023

    2023

  16. [16]

    Unlocking attributes’ contribution to successful camouflage: A com- bined textual and visual analysis strategy,

    H. Zhang, Y . Lyu, Q. Yu, H. Liu, H. Ma, D. Yuan, and Y . Yang, “Unlocking attributes’ contribution to successful camouflage: A com- bined textual and visual analysis strategy,” inEuropean Conference on Computer Vision. Springer, 2024, pp. 315–331

    2024

  17. [17]

    Upgen: Unleashing potential of foundation models for training- free camouflage detection via generative models,

    J. Du, J. Wu, D. Kong, W. Liang, F. Hao, J. Xu, B. Wang, G. Wang, and P. Li, “Upgen: Unleashing potential of foundation models for training- free camouflage detection via generative models,”IEEE Transactions on Image Processing, 2025

    2025

  18. [18]

    Just a hint: Point-supervised camouflaged object detection,

    H. Chen, D. Shao, G. Guo, and S. Gao, “Just a hint: Point-supervised camouflaged object detection,” inEuropean Conference on Computer Vision. Springer, 2024, pp. 332–348

    2024

  19. [19]

    Think twice before determining: Towards scene-aware visual reasoning for mirror detection,

    M. Zha, G. Wang, Y . Pei, T. Li, X. Tang, J. Ma, Y . Yang, and H. T. Shen, “Think twice before determining: Towards scene-aware visual reasoning for mirror detection,”IEEE Transactions on Circuits and Systems for Video Technology, 2026

    2026

  20. [20]

    Camoteacher: Dual-rotation consistency learning for semi- supervised camouflaged object detection,

    X. Lai, Z. Yang, J. Hu, S. Zhang, L. Cao, G. Jiang, Z. Wang, S. Zhang, and R. Ji, “Camoteacher: Dual-rotation consistency learning for semi- supervised camouflaged object detection,” inEuropean Conference on Computer Vision. Springer, 2024, pp. 438–455

    2024

  21. [21]

    Zero-shot camouflaged object detection,

    H. Li, C.-M. Feng, Y . Xu, T. Zhou, L. Yao, and X. Chang, “Zero-shot camouflaged object detection,”IEEE Transactions on Image Processing, vol. 32, pp. 5126–5137, 2023

    2023

  22. [22]

    Few-shot camouflaged object segmentation,

    Z. Wang, Y . Li, Y . Yang, Y . Li, and G. Liu, “Few-shot camouflaged object segmentation,” in2024 International Joint Conference on Neural Networks (IJCNN). IEEE, 2024, pp. 1–10

    2024

  23. [23]

    Focus- diffuser: Perceiving local disparities for camouflaged object detection,

    J. Zhao, X. Li, F. Yang, Q. Zhai, A. Luo, Z. Jiao, and H. Cheng, “Focus- diffuser: Perceiving local disparities for camouflaged object detection,” inEuropean Conference on Computer Vision. Springer, 2024, pp. 181– 198

    2024

  24. [24]

    Sam-cod+: Sam-guided unified framework for weakly-supervised camouflaged object detection,

    H. Chen, P. Wei, G. Guo, and S. Gao, “Sam-cod+: Sam-guided unified framework for weakly-supervised camouflaged object detection,”IEEE Transactions on Circuits and Systems for Video Technology, 2024

    2024

  25. [25]

    Vscode: General visual salient and camouflaged object detection with 2d prompt learning,

    Z. Luo, N. Liu, W. Zhao, X. Yang, D. Zhang, D.-P. Fan, F. Khan, and J. Han, “Vscode: General visual salient and camouflaged object detection with 2d prompt learning,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2024, pp. 17 169–17 180

    2024

  26. [26]

    Comprompter: reconceptualized segment anything model with multiprompt network for camouflaged object detection,

    X. Zhang, Z. Yu, L. Zhao, D.-P. Fan, and G. Xiao, “Comprompter: reconceptualized segment anything model with multiprompt network for camouflaged object detection,”Science China Information Sciences, vol. 68, no. 1, p. 112104, 2025

    2025

  27. [27]

    Text-prompt camouflaged instance segmentation with graduated camouflage learning,

    Z. He, C. Xia, S. Qiao, and J. Li, “Text-prompt camouflaged instance segmentation with graduated camouflage learning,” inProceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 5584– 5593

    2024

  28. [28]

    Endow sam with keen eyes: Temporal-spatial prompt learning for video camouflaged object detection,

    W. Hui, Z. Zhu, S. Zheng, and Y . Zhao, “Endow sam with keen eyes: Temporal-spatial prompt learning for video camouflaged object detection,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 19 058–19 067

    2024

  29. [29]

    Explicit motion handling and interactive prompting for video camouflaged object detection,

    X. Zhang, T. Xiao, G.-P. Ji, X. Wu, K. Fu, and Q. Zhao, “Explicit motion handling and interactive prompting for video camouflaged object detection,”IEEE Transactions on Image Processing, 2025

    2025

  30. [30]

    Depth-aware concealed crop detection in dense agricultural scenes,

    L. Wang, J. Yang, Y . Zhang, F. Wang, and F. Zheng, “Depth-aware concealed crop detection in dense agricultural scenes,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 17 201–17 211

    2024

  31. [31]

    A simple yet effective network based on vision transformer for camouflaged object and salient object detection,

    C. Hao, Z. Yu, X. Liu, J. Xu, H. Yue, and J. Yang, “A simple yet effective network based on vision transformer for camouflaged object and salient object detection,”IEEE Transactions on Image Processing, 2025

    2025

  32. [32]

    Open-vocabulary cam- ouflaged object segmentation,

    Y . Pang, X. Zhao, J. Zuo, L. Zhang, and H. Lu, “Open-vocabulary cam- ouflaged object segmentation,” inEuropean Conference on Computer Vision. Springer, 2024, pp. 476–495

    2024

  33. [33]

    Learning transferable visual models from natural language supervision,

    A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clarket al., “Learning transferable visual models from natural language supervision,” inInternational conference on machine learning. PMLR, 2021, pp. 8748–8763

    2021

  34. [34]

    Tent: Fully Test-time Adaptation by Entropy Minimization

    D. Wang, E. Shelhamer, S. Liu, B. Olshausen, and T. Darrell, “Tent: Fully test-time adaptation by entropy minimization,”arXiv preprint arXiv:2006.10726, 2020

    work page internal anchor Pith review Pith/arXiv arXiv 2006

  35. [35]

    Test-time adaptation via self-training with nearest neighbor information,

    M. Jang, S.-Y . Chung, and H. W. Chung, “Test-time adaptation via self-training with nearest neighbor information,”arXiv preprint arXiv:2207.10792, 2022

    work page arXiv 2022

  36. [36]

    A probabilistic framework for lifelong test-time adaptation,

    D. Brahma and P. Rai, “A probabilistic framework for lifelong test-time adaptation,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 3582–3591

    2023

  37. [37]

    Delta: degradation-free fully test-time adaptation,

    B. Zhao, C. Chen, and S.-T. Xia, “Delta: degradation-free fully test-time adaptation,”arXiv preprint arXiv:2301.13018, 2023

    work page arXiv 2023

  38. [38]

    Improved self-training for test-time adaptation,

    J. Ma, “Improved self-training for test-time adaptation,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recogni- tion, 2024, pp. 23 701–23 710

    2024

  39. [39]

    Depth- aware test-time training for zero-shot video object segmentation,

    W. Liu, X. Shen, H. Li, X. Bi, B. Liu, C.-M. Pun, and X. Cun, “Depth- aware test-time training for zero-shot video object segmentation,” in 15 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 19 218–19 227

    2024

  40. [40]

    Relax image-specific prompt requirement in sam: A single generic prompt for segmenting camou- flaged objects,

    J. Hu, J. Lin, S. Gong, and W. Cai, “Relax image-specific prompt requirement in sam: A single generic prompt for segmenting camou- flaged objects,” inProceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 11, 2024, pp. 12 511–12 518

    2024

  41. [41]

    Focal frequency loss for image reconstruction and synthesis,

    L. Jiang, B. Dai, W. Wu, and C. C. Loy, “Focal frequency loss for image reconstruction and synthesis,” inProceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 13 919–13 929

    2021

  42. [42]

    Zoom in and out: A mixed-scale triplet network for camouflaged object detection,

    Y . Pang, X. Zhao, T.-Z. Xiang, L. Zhang, and H. Lu, “Zoom in and out: A mixed-scale triplet network for camouflaged object detection,” inProceedings of the IEEE/CVF Conference on computer vision and pattern recognition, 2022, pp. 2160–2170

    2022

  43. [43]

    Cam- ouflaged object detection,

    D.-P. Fan, G.-P. Ji, G. Sun, M.-M. Cheng, J. Shen, and L. Shao, “Cam- ouflaged object detection,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 2777–2787

    2020

  44. [44]

    Mutual graph learning for camouflaged object detection,

    Q. Zhai, X. Li, F. Yang, C. Chen, H. Cheng, and D.-P. Fan, “Mutual graph learning for camouflaged object detection,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 12 997–13 007

    2021

  45. [45]

    Camouflaged object segmentation with distraction mining,

    H. Mei, G.-P. Ji, Z. Wei, X. Yang, X. Wei, and D.-P. Fan, “Camouflaged object segmentation with distraction mining,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 8772–8781

    2021

  46. [46]

    Uncertainty-guided transformer reasoning for camouflaged object detection,

    F. Yang, Q. Zhai, X. Li, R. Huang, A. Luo, H. Cheng, and D.-P. Fan, “Uncertainty-guided transformer reasoning for camouflaged object detection,” inProceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 4146–4155

    2021

  47. [47]

    Simultaneously localize, segment and rank the camouflaged objects,

    Y . Lv, J. Zhang, Y . Dai, A. Li, B. Liu, N. Barnes, and D.-P. Fan, “Simultaneously localize, segment and rank the camouflaged objects,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 11 591–11 601

    2021

  48. [48]

    Concealed object detec- tion,

    D.-P. Fan, G.-P. Ji, M.-M. Cheng, and L. Shao, “Concealed object detec- tion,”IEEE transactions on pattern analysis and machine intelligence, vol. 44, no. 10, pp. 6024–6042, 2021

    2021

  49. [49]

    Preynet: Preying on camouflaged objects,

    M. Zhang, S. Xu, Y . Piao, D. Shi, S. Lin, and H. Lu, “Preynet: Preying on camouflaged objects,” inProceedings of the 30th ACM international conference on multimedia, 2022, pp. 5323–5332

    2022

  50. [50]

    Camouflaged object detection with feature decomposition and edge re- construction,

    C. He, K. Li, Y . Zhang, L. Tang, Y . Zhang, Z. Guo, and X. Li, “Camouflaged object detection with feature decomposition and edge re- construction,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2023, pp. 22 046–22 055

    2023

  51. [51]

    Run: Reversible unfolding network for concealed object segmentation,

    C. He, R. Zhang, F. Xiao, C. Fang, L. Tang, Y . Zhang, L. Kong, D.- P. Fan, K. Li, and S. Farsiu, “Run: Reversible unfolding network for concealed object segmentation,”arXiv preprint arXiv:2501.18783, 2025

    work page arXiv 2025

  52. [52]

    Segment anything,

    A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, T. Xiao, S. Whitehead, A. C. Berg, W.-Y . Loet al., “Segment anything,” inProceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 4015–4026

    2023

  53. [53]

    High-resolution iterative feedback network for camouflaged object detection,

    X. Hu, S. Wang, X. Qin, H. Dai, W. Ren, D. Luo, Y . Tai, and L. Shao, “High-resolution iterative feedback network for camouflaged object detection,” inProceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 1, 2023, pp. 881–889

    2023

  54. [54]

    Frequency perception network for camouflaged object detection,

    R. Cong, M. Sun, S. Zhang, X. Zhou, W. Zhang, and Y . Zhao, “Frequency perception network for camouflaged object detection,” in Proceedings of the 31st ACM international conference on multimedia, 2023, pp. 1179–1189

    2023

  55. [55]

    Feature shrinkage pyramid for camouflaged object detection with transformers,

    Z. Huang, H. Dai, T.-Z. Xiang, S. Wang, H.-X. Chen, J. Qin, and H. Xiong, “Feature shrinkage pyramid for camouflaged object detection with transformers,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2023, pp. 5557–5566

    2023

  56. [56]

    Explicit visual prompting for low-level structure segmentations,

    W. Liu, X. Shen, C.-M. Pun, and X. Cun, “Explicit visual prompting for low-level structure segmentations,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 19 434–19 445

    2023

  57. [57]

    Camoformer: Masked separable attention for camouflaged object detection,

    B. Yin, X. Zhang, D.-P. Fan, S. Jiao, M.-M. Cheng, L. Van Gool, and Q. Hou, “Camoformer: Masked separable attention for camouflaged object detection,”IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024

    2024

  58. [58]

    Spi- der: A unified framework for context-dependent concept segmentation,

    X. Zhao, Y . Pang, W. Ji, B. Sheng, J. Zuo, L. Zhang, and H. Lu, “Spider: A unified framework for context-dependent concept understanding,” arXiv preprint arXiv:2405.01002, 2024

    work page arXiv 2024

  59. [59]

    Exploring deeper! segment anything model with depth perception for camouflaged object detection,

    Z. Yu, X. Zhang, L. Zhao, Y . Bin, and G. Xiao, “Exploring deeper! segment anything model with depth perception for camouflaged object detection,” inProceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 4322–4330

    2024

  60. [60]

    Conditional diffusion models for camouflaged and salient object detection,

    K. Sun, Z. Chen, X. Lin, X. Sun, H. Liu, and R. Ji, “Conditional diffusion models for camouflaged and salient object detection,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 4, pp. 2833–2848, 2025

    2025

  61. [61]

    Rethinking detecting salient and camouflaged objects in unconstrained scenes,

    Z. Zhou, Y . Li, C. Zhong, J. Huang, J. Pei, H. Li, and H. Tang, “Rethinking detecting salient and camouflaged objects in unconstrained scenes,” inProceedings of the IEEE/CVF International Conference on Computer Vision, 2025, pp. 22 372–22 382

    2025

  62. [62]

    Multi-modal segment anything model for camouflaged scene segmentation,

    G. Ren, H. Liu, M. Lazarou, and T. Stathaki, “Multi-modal segment anything model for camouflaged scene segmentation,” inProceedings of the IEEE/CVF International Conference on Computer Vision, 2025, pp. 19 882–19 892

    2025

  63. [63]

    Sam-ttt: Segment anything model via reverse parameter configuration and test-time training for cam- ouflaged object detection,

    Z. Yu, L. Zhao, G. Xiao, and X. Zhang, “Sam-ttt: Segment anything model via reverse parameter configuration and test-time training for cam- ouflaged object detection,” inProceedings of the 33rd ACM International Conference on Multimedia, 2025, pp. 4030–4038

    2025

  64. [64]

    Vision transformers for dense prediction,

    R. Ranftl, A. Bochkovskiy, and V . Koltun, “Vision transformers for dense prediction,” inProceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 12 179–12 188

    2021

  65. [65]

    Anabranch network for camouflaged object segmentation,

    T.-N. Le, T. V . Nguyen, Z. Nie, M.-T. Tran, and A. Sugimoto, “Anabranch network for camouflaged object segmentation,”Computer vision and image understanding, vol. 184, pp. 45–56, 2019

    2019

  66. [66]

    Animal camouflage analysis: Chameleon database,

    P. Skurowski, H. Abdulameer, J. Błaszczyk, T. Depta, A. Kornacki, and P. Kozieł, “Animal camouflage analysis: Chameleon database,” Unpublished manuscript, vol. 2, no. 6, p. 7, 2018

    2018

  67. [67]

    Mas3k: An open dataset for marine animal segmentation,

    L. Li, E. Rigall, J. Dong, and G. Chen, “Mas3k: An open dataset for marine animal segmentation,” inInternational Symposium on Bench- marking, Measuring and Optimization. Springer, 2020, pp. 194–212

    2020

  68. [68]

    Masnet: A robust deep marine animal segmentation network,

    Z. Fu, R. Chen, Y . Huang, E. Cheng, X. Ding, and K.-K. Ma, “Masnet: A robust deep marine animal segmentation network,”IEEE Journal of Oceanic Engineering, 2023

    2023

  69. [69]

    Simultaneous enhancement and super- resolution of underwater imagery for improved visual perception,

    M. J. Islam, P. Luo, and J. Sattar, “Simultaneous enhancement and super- resolution of underwater imagery for improved visual perception,”arXiv preprint arXiv:2002.01155, 2020

    work page arXiv 2002

  70. [70]

    Underwater image segmentation in the wild using deep learning,

    P. Drews-Jr, I. d. Souza, I. P. Maurell, E. V . Protas, and S. S. C. Botelho, “Underwater image segmentation in the wild using deep learning,” Journal of the Brazilian Computer Society, vol. 27, pp. 1–14, 2021

    2021

  71. [71]

    Benchmarking Neural Network Robustness to Common Corruptions and Perturbations

    D. Hendrycks and T. Dietterich, “Benchmarking neural network ro- bustness to common corruptions and perturbations,”arXiv preprint arXiv:1903.12261, 2019

    work page internal anchor Pith review Pith/arXiv arXiv 1903

  72. [72]

    Learning to adapt using test-time images for salient object detection in optical remote sensing images,

    K. Huang, L. Fang, and C. Tian, “Learning to adapt using test-time images for salient object detection in optical remote sensing images,” IEEE Transactions on Geoscience and Remote Sensing, 2024

    2024

  73. [73]

    Pvt v2: Improved baselines with pyramid vision transformer,

    W. Wang, E. Xie, X. Li, D.-P. Fan, K. Song, D. Liang, T. Lu, P. Luo, and L. Shao, “Pvt v2: Improved baselines with pyramid vision transformer,” Computational Visual Media, vol. 8, no. 3, pp. 415–424, 2022

    2022

  74. [74]

    Deep residual learning for image recognition,

    K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” inProceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778

    2016

  75. [75]

    Auto-Encoding Variational Bayes,

    D. P. Kingma and M. Welling, “Auto-Encoding Variational Bayes,” in 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings, 2014

    2014

  76. [76]

    The norm must go on: Dynamic unsupervised domain adaptation by normalization,

    M. J. Mirza, J. Micorek, H. Possegger, and H. Bischof, “The norm must go on: Dynamic unsupervised domain adaptation by normalization,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 14 765–14 775

    2022

  77. [77]

    Gradient harmonization in unsuper- vised domain adaptation,

    F. Huang, S. Song, and L. Zhang, “Gradient harmonization in unsuper- vised domain adaptation,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 12, pp. 10 319–10 336, 2024

    2024

  78. [78]

    Ttt-mim: Test-time training with masked image modeling for denoising distribution shifts,

    Y . Mansour, X. Zhong, S. Caglar, and R. Heckel, “Ttt-mim: Test-time training with masked image modeling for denoising distribution shifts,” inEuropean Conference on Computer Vision. Springer, 2024, pp. 341– 357

    2024

  79. [79]

    Fantastic animals and where to find them: Segment any marine animal with dual sam,

    P. Zhang, T. Yan, Y . Liu, and H. Lu, “Fantastic animals and where to find them: Segment any marine animal with dual sam,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 2578–2587

    2024

  80. [80]

    Mas-sam: Segment any marine animal with aggregated features,

    T. Yan, Z. Wan, X. Deng, P. Zhang, Y . Liu, and H. Lu, “Mas-sam: Segment any marine animal with aggregated features,”arXiv preprint arXiv:2404.15700, 2024

    work page arXiv 2024

Showing first 80 references.