pith. sign in

arxiv: 2607.01870 · v1 · pith:BKQPIYIFnew · submitted 2026-07-02 · 💻 cs.AI

CamoNAS: Neural Architecture Search for Enhanced Camouflaged Object Detection

Dawei Ren , Yan Zhang , Hongying Tang , Qiaoling Zhou , Jianpo Liu This is my paper

Pith reviewed 2026-07-03 13:16 UTC · model grok-4.3

classification 💻 cs.AI
keywords camouflaged object detectionneural architecture searchfrequency domainwavelet transformdual-stream networkhierarchical search spacebenchmark evaluation
0
0 comments X

The pith

CamoNAS applies neural architecture search over a hierarchical space with a frequency-aware dual-stream design to reach state-of-the-art results on camouflaged object detection.

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

The paper replaces hand-designed architectures for camouflaged object detection with an automated search process that jointly optimizes cell operations and network downsampling paths. It adds a dual-stream backbone in which a learnable wavelet transform supplies frequency information alongside the usual RGB spatial stream. A reader would care because camouflaged objects present weak edges and ill-defined boundaries that intuition-based multi-scale fusion often fails to handle well. If the approach works, it demonstrates that domain-specific NAS can systematically discover better feature combinations than manual design for tasks where visual cues are subtle.

Core claim

CamoNAS builds a hierarchical search space that searches both cell-level operations and network-level downsampling paths, then trains an RGB frequency dual-stream network whose second stream uses a learnable wavelet transform; the resulting architectures reach state-of-the-art performance on the CAMO, COD10K, NC4K, and CHAMELEON benchmarks.

What carries the argument

Hierarchical search space over cell operations and downsampling paths together with an RGB frequency dual-stream architecture driven by a learnable wavelet transform.

If this is right

  • The searched architectures outperform prior hand-designed COD models on all four standard benchmarks.
  • Frequency information from the wavelet stream improves handling of weak boundary cues.
  • Joint search over cell operations and downsampling paths produces task-specific multi-resolution structures.
  • NAS can replace intuition-driven multi-scale fusion in domains with ill-defined object boundaries.

Where Pith is reading between the lines

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

  • The same frequency-augmented search could be tested on texture-blending problems outside natural images, such as anomaly detection in medical scans.
  • If the hierarchical space proves reusable, it could reduce the need for repeated manual redesign when applying NAS to new detection tasks with scale variation.
  • The dual-stream pattern suggests that explicit separation of spatial and frequency processing may be worth testing in other low-contrast segmentation settings.

Load-bearing premise

The performance gains arise from the frequency-aware hierarchical NAS design rather than from hyper-parameter tuning volume or from particular properties of the four benchmarks.

What would settle it

A controlled comparison in which a manually designed dual-stream network with matched compute budget and similar hyper-parameter search effort is evaluated on the same four benchmarks and matches or exceeds CamoNAS scores.

read the original abstract

Camouflaged Object Detection (COD) aims to locate and segment objects that blend into their surroundings, presenting challenges due to weak edge cues and ill-defined boundaries. Traditional COD models rely on hand-designed architectures and multi-scale feature fusion, which are often guided by intuition rather than systematic search. This paper introduces CamoNAS, a frequency-aware multi-resolution Neural Architecture Search (NAS) framework for COD. CamoNAS automatically searches both cell-level operations and network-level downsampling paths, forming a hierarchical search space tailored to detect camouflaged objects. Additionally, it adopts an RGB frequency dual-stream architecture, where a learnable wavelet transform complements the RGB spatial stream. CamoNAS achieves state-of-the-art performance on four COD benchmarks (CAMO, COD10K, NC4K, CHAMELEON), highlighting the effectiveness of NAS for COD. Our code is available at https://github.com/rendaweiSIMIT/CamoNAS.

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

2 major / 2 minor

Summary. The paper introduces CamoNAS, a frequency-aware multi-resolution Neural Architecture Search (NAS) framework for Camouflaged Object Detection (COD). It automatically searches cell-level operations and network-level downsampling paths in a hierarchical space, combined with an RGB-frequency dual-stream architecture that incorporates a learnable wavelet transform. The central claim is that this yields state-of-the-art performance on the CAMO, COD10K, NC4K, and CHAMELEON benchmarks, with code released publicly.

Significance. If the reported gains are shown to stem specifically from the hierarchical NAS and dual-stream design rather than generic tuning, the work would demonstrate that systematic architecture search can improve upon hand-designed models in a domain characterized by weak boundaries and low-contrast cues. The public code release supports reproducibility and is a clear strength.

major comments (2)
  1. [§4] §4 (Experiments): No control experiment is reported in which a fixed, hand-designed backbone (e.g., a standard ResNet or the authors' own dual-stream RGB baseline) receives an equivalent hyperparameter and augmentation search budget; without this, the necessity of the proposed cell-level and network-level search space for the SOTA margins cannot be isolated from tuning effects.
  2. [Table 2] Table 2 (main results): Performance deltas versus prior SOTA are presented as single-point estimates without standard deviations across multiple random seeds or statistical significance tests; given the small margins typical in COD benchmarks, this weakens the claim that CamoNAS is reliably superior.
minor comments (2)
  1. [§3.2] §3.2: The description of the learnable wavelet transform lacks an explicit equation for the frequency decomposition; adding this would clarify how the dual-stream fusion is implemented.
  2. [Figure 3] Figure 3: The diagram of the hierarchical search space would benefit from clearer labeling of the cell-level versus network-level search dimensions.

Simulated Author's Rebuttal

2 responses · 0 unresolved

Thank you for the detailed review. We have carefully considered the major comments and provide point-by-point responses below. We propose partial revisions to address the concerns where feasible.

read point-by-point responses

  1. Referee: [§4] §4 (Experiments): No control experiment is reported in which a fixed, hand-designed backbone (e.g., a standard ResNet or the authors' own dual-stream RGB baseline) receives an equivalent hyperparameter and augmentation search budget; without this, the necessity of the proposed cell-level and network-level search space for the SOTA margins cannot be isolated from tuning effects.

    Authors: We appreciate this point. Our primary contribution is the introduction of the hierarchical NAS framework tailored for COD, and the comparisons are made against published SOTA methods using their reported settings. To better isolate the effect, we will add a discussion in the revised manuscript explaining that the dual-stream baseline is our own design without NAS, and the performance gains are attributed to the searched architectures. However, conducting a full hyperparameter search on a fixed backbone would require substantial additional resources beyond the scope of this work. revision: partial

  2. Referee: [Table 2] Table 2 (main results): Performance deltas versus prior SOTA are presented as single-point estimates without standard deviations across multiple random seeds or statistical significance tests; given the small margins typical in COD benchmarks, this weakens the claim that CamoNAS is reliably superior.

    Authors: We acknowledge that reporting standard deviations would provide stronger evidence of reliability. In the COD literature, it is common to report single-run results due to the high computational demands of training deep models on these benchmarks. Our results show consistent improvements across four different datasets, which supports the robustness. We will add a note in the revised paper acknowledging this limitation and suggesting future work on statistical validation. revision: partial

Circularity Check

0 steps flagged

No circularity; empirical NAS results with no derived quantities

full rationale

The paper describes an empirical NAS method (CamoNAS) that searches cell-level operations and network-level paths in a frequency-aware dual-stream architecture, then reports benchmark performance. No equations, first-principles derivations, or predictions appear in the provided text. Performance numbers are presented as search outcomes rather than quantities fitted or defined in terms of themselves. No self-citation load-bearing steps, ansatz smuggling, or renaming of known results are evident. The derivation chain is self-contained as an engineering search procedure.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The central claim rests on the existence of a well-behaved search space whose optimal architecture yields measurable gains on the chosen benchmarks; no explicit free parameters, axioms, or invented entities are stated in the abstract.

pith-pipeline@v0.9.1-grok · 5698 in / 1089 out tokens · 26458 ms · 2026-07-03T13:16:48.407167+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

86 extracted references · 86 canonical work pages · 4 internal anchors

  1. [1]

    IEEE transactions on pattern analysis and machine intelligence44(10), 6024–6042 (2021)

    Fan, D.-P., Ji, G.-P., Cheng, M.-M., Shao, L.: Concealed object detection. IEEE transactions on pattern analysis and machine intelligence44(10), 6024–6042 (2021)

    work page 2021

  2. [2]

    In: CVPR, pp

    Fan, D.-P., Ji, G.-P., Sun, G., Cheng, M.-M., Shen, J., Shao, L.: Camouflaged object detection. In: CVPR, pp. 2777–2787 (2020) 15

    work page 2020

  3. [3]

    In: ICCV, pp

    Yang, F., Zhai, Q., Li, X., Huang, R., Luo, A., Cheng, H., Fan, D.-P.: Uncertainty- guided transformer reasoning for camouflaged object detection. In: ICCV, pp. 4146–4155 (2021)

    work page 2021

  4. [4]

    In: MICCAI, pp

    Fan, D.-P., Ji, G.-P., Zhou, T., Chen, G., Fu, H., Shen, J., Shao, L.: Pranet: Parallel reverse attention network for polyp segmentation. In: MICCAI, pp. 263– 273 (2020). Springer

    work page 2020

  5. [5]

    In: MICCAI, pp

    Zhang, R., Li, G., Li, Z., Cui, S., Qian, D., Yu, Y.: Adaptive context selection for polyp segmentation. In: MICCAI, pp. 253–262 (2020). Springer

    work page 2020

  6. [6]

    In: CVPR, pp

    Mei, H., Yang, X., Wang, Y., Liu, Y., He, S., Zhang, Q., Wei, X., Lau, R.W.: Don’t hit me! glass detection in real-world scenes. In: CVPR, pp. 3687–3696 (2020)

    work page 2020

  7. [7]

    In: ECCV (2020)

    Xie, E., Wang, W., Wang, W., Ding, M., Shen, C., Luo, P.: Segmenting transparent objects in the wild. In: ECCV (2020). Springer

    work page 2020

  8. [8]

    In: ACM MM, pp

    Zhang, M., Xu, S., Piao, Y., Shi, D., Lin, S., Lu, H.: Preynet: Preying on camouflaged objects. In: ACM MM, pp. 5323–5332 (2022)

    work page 2022

  9. [9]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Mei, H., Ji, G.-P., Wei, Z., Yang, X., Wei, X., Fan, D.-P.: Camouflaged object seg- mentation with distraction mining. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8772–8781 (2021)

    work page 2021

  10. [10]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Pang, Y., Zhao, X., Xiang, T.-Z., Zhang, L., Lu, H.: Zoom in and out: A mixed- scale triplet network for camouflaged object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2160– 2170 (2022)

    work page 2022

  11. [11]

    Scientific Reports15(1), 2735 (2025)

    Cheng, A., Wu, S., Liu, X., Lu, H.: Enhancing concealed object detection in active thz security images with adaptation-yolo. Scientific Reports15(1), 2735 (2025)

    work page 2025

  12. [12]

    Engineering Applications of Artificial Intelligence158, 111462 (2025)

    Kowalski, M., Mierzejewski, K., Pa lys, T.: Bi-spectral concealed object detection with attention-based fusion of passive thermal infrared and terahertz imaging. Engineering Applications of Artificial Intelligence158, 111462 (2025)

    work page 2025

  13. [13]

    In: 2022 26th International Conference on Pattern Recognition (ICPR), pp

    Liu, Z., Zhang, Z., Tan, Y., Wu, W.: Boosting camouflaged object detection with dual-task interactive transformer. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 140–146 (2022). IEEE

    work page 2022

  14. [14]

    In: CVPR, pp

    Zhong, Y., Li, B., Tang, L., Kuang, S., Wu, S., Ding, S.: Detecting camouflaged object in frequency domain. In: CVPR, pp. 4504–4513 (2022)

    work page 2022

  15. [15]

    In: CVPR (2023)

    He, C., Li, K., Zhang, Y., Tang, L., Zhang, Y., Guo, Z., Li, X.: Camouflaged object detection with feature decomposition and edge reconstruction. In: CVPR (2023)

    work page 2023

  16. [16]

    In: CVPR, pp

    Zhai, Q., Li, X., Yang, F., Chen, C., Cheng, H., Fan, D.-P.: Mutual graph learning 16 for camouflaged object detection. In: CVPR, pp. 12997–13007 (2021)

    work page 2021

  17. [17]

    arXiv preprint arXiv:2207.00794 (2022)

    Sun, Y., Wang, S., Chen, C., Xiang, T.-Z.: Boundary-guided camouflaged object detection. arXiv preprint arXiv:2207.00794 (2022)

    work page arXiv 2022

  18. [18]

    In: NIPS, vol

    Zhai, W., Cao, Y., Zhang, J., Zha, Z.-J.: Exploring figure-ground assignment mechanism in perceptual organization. In: NIPS, vol. 35 (2022)

    work page 2022

  19. [19]

    In: CVPR, pp

    Lv, Y., Zhang, J., Dai, Y., Li, A., Liu, B., Barnes, N., Fan, D.-P.: Simultaneously localize, segment and rank the camouflaged objects. In: CVPR, pp. 11591–11601 (2021)

    work page 2021

  20. [20]

    In: CVPR, pp

    Jia, Q., Yao, S., Liu, Y., Fan, X., Liu, R., Luo, Z.: Segment, magnify and reiterate: Detecting camouflaged objects the hard way. In: CVPR, pp. 4713–4722 (2022)

    work page 2022

  21. [21]

    In: AAAI, vol

    Zhu, H., Li, P., Xie, H., Yan, X., Liang, D., Chen, D., Wei, M., Qin, J.: I can find you! boundary-guided separated attention network for camouflaged object detection. In: AAAI, vol. 36, pp. 3608–3616 (2022)

    work page 2022

  22. [22]

    Journal of Machine Learning Research20(55), 1–21 (2019)

    Elsken, T., Metzen, J.H., Hutter, F.: Neural architecture search: A survey. Journal of Machine Learning Research20(55), 1–21 (2019)

    work page 2019

  23. [23]

    Neural Architecture Search with Reinforcement Learning

    Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  24. [24]

    In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp

    Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architec- tures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697–8710 (2018)

    work page 2018

  25. [25]

    In: Proceedings of the European Conference on Computer Vision (ECCV), pp

    Liu, C., Zoph, B., Neumann, M., Shlens, J., Hua, W., Li, L.-J., Fei-Fei, L., Yuille, A., Huang, J., Murphy, K.: Progressive neural architecture search. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 19–34 (2018)

    work page 2018

  26. [26]

    In: Proceedings of the Aaai Conference on Artificial Intelligence, vol

    Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. In: Proceedings of the Aaai Conference on Artificial Intelligence, vol. 33, pp. 4780–4789 (2019)

    work page 2019

  27. [27]

    In: International Conference on Machine Learning, pp

    Pham, H., Guan, M., Zoph, B., Le, Q., Dean, J.: Efficient neural architecture search via parameters sharing. In: International Conference on Machine Learning, pp. 4095–4104 (2018). PMLR

    work page 2018

  28. [29]

    In: Proceedings of the IEEE/CVF Conference 17 on Computer Vision and Pattern Recognition, pp

    Zhang, Y., Qiu, Z., Liu, J., Yao, T., Liu, D., Mei, T.: Customizable architecture search for semantic segmentation. In: Proceedings of the IEEE/CVF Conference 17 on Computer Vision and Pattern Recognition, pp. 11641–11650 (2019)

    work page 2019

  29. [30]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Nekrasov, V., Chen, H., Shen, C., Reid, I.: Fast neural architecture search of compact semantic segmentation models via auxiliary cells. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9126–9135 (2019)

    work page 2019

  30. [31]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Lin, P., Sun, P., Cheng, G., Xie, S., Li, X., Shi, J.: Graph-guided architecture search for real-time semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4203–4212 (2020)

    work page 2020

  31. [32]

    DARTS: Differentiable Architecture Search

    Liu, H., Simonyan, K., Yang, Y.: Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  32. [33]

    In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp

    Li, X., Fu, K., Zhao, Q.: Camouflaged object detection via neural architec- ture search. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1–5 (2025). IEEE

    work page 2025

  33. [34]

    Neurocomputing 566, 127050 (2024)

    Liang, Y., Qin, G., Sun, M., Wang, X., Yan, J., Zhang, Z.: A systematic review of image-level camouflaged object detection with deep learning. Neurocomputing 566, 127050 (2024)

    work page 2024

  34. [35]

    In: Proceedings of the 31st ACM International Conference on Multimedia, pp

    Cong, R., Sun, M., Zhang, S., Zhou, X., Zhang, W., Zhao, Y.: Frequency percep- tion network for camouflaged object detection. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 1179–1189 (2023)

    work page 2023

  35. [36]

    In: Proceedings of the 31st ACM International Conference on Multimedia, pp

    Xie, C., Xia, C., Yu, T., Li, J.: Frequency representation integration for camou- flaged object detection. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 1789–1797 (2023)

    work page 2023

  36. [37]

    ACM Computing Surveys (CSUR)47(2), 1–33 (2014)

    Zhou, X., Yang, C., Zhao, H., Yu, W.: Low-rank modeling and its applications in image analysis. ACM Computing Surveys (CSUR)47(2), 1–33 (2014)

    work page 2014

  37. [38]

    IEEE transactions on circuits and systems for video technology32(9), 5708–5724 (2021)

    Bi, H., Zhang, C., Wang, K., Tong, J., Zheng, F.: Rethinking camouflaged object detection: Models and datasets. IEEE transactions on circuits and systems for video technology32(9), 5708–5724 (2021)

    work page 2021

  38. [39]

    International Journal of Computer Vision122(1), 116–148 (2017)

    Mondal, A., Ghosh, S., Ghosh, A.: Partially camouflaged object tracking using modified probabilistic neural network and fuzzy energy based active contour. International Journal of Computer Vision122(1), 116–148 (2017)

    work page 2017

  39. [40]

    IEEE Transactions on Image Processing27(8), 3918–3930 (2018)

    Li, S., Florencio, D., Li, W., Zhao, Y., Cook, C.: A fusion framework for cam- ouflaged moving foreground detection in the wavelet domain. IEEE Transactions on Image Processing27(8), 3918–3930 (2018)

    work page 2018

  40. [41]

    Computer vision and image understanding 18 184, 45–56 (2019)

    Le, T.-N., Nguyen, T.V., Nie, Z., Tran, M.-T., Sugimoto, A.: Anabranch network for camouflaged object segmentation. Computer vision and image understanding 18 184, 45–56 (2019)

    work page 2019

  41. [42]

    IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)

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

    work page 2024

  42. [43]

    The Visual Computer41(6), 3957–3972 (2025)

    Yue, G., Jiao, G., Li, C., Xiang, J.: When cnn meet with vit: decision-level feature fusion for camouflaged object detection. The Visual Computer41(6), 3957–3972 (2025)

    work page 2025

  43. [44]

    The Visual Computer 41(7), 4741–4758 (2025)

    Ge, Y., Ren, J., Zhang, C., He, M., Bi, H., Zhang, Q.: Feature-aware and itera- tive refinement network for camouflaged object detection. The Visual Computer 41(7), 4741–4758 (2025)

    work page 2025

  44. [45]

    Unpublished manuscript 2(6), 7 (2018)

    Skurowski, P., Abdulameer, H., B laszczyk, J., Depta, T., Kornacki, A., Kozie l, P.: Animal camouflage analysis: Chameleon database. Unpublished manuscript 2(6), 7 (2018)

    work page 2018

  45. [46]

    In: CVPR, pp

    Lin, J., He, Z., Lau, R.W.: Rich context aggregation with reflection prior for glass surface detection. In: CVPR, pp. 13415–13424 (2021)

    work page 2021

  46. [47]

    In: International Conference on Medical Image Computing and Computer-assisted Intervention, pp

    Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-assisted Intervention, pp. 234–241 (2015). Springer

    work page 2015

  47. [48]

    IEEE transactions on pattern analysis and machine intelligence40(4), 834–848 (2017)

    Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence40(4), 834–848 (2017)

    work page 2017

  48. [49]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Kirillov, A., Wu, Y., He, K., Girshick, R.: Pointrend: Image segmentation as rendering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9799–9808 (2020)

    work page 2020

  49. [50]

    In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp

    Lin, T.-Y., Doll´ ar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)

    work page 2017

  50. [51]

    Virtual Reality & Intelligent Hardware5(1), 57–67 (2023) https://doi.org/10.1016/j.vrih.2022.07.006

    Zhang, M., Tian, X.: Transformer architecture based on mutual attention for image-anomaly detection. Virtual Reality & Intelligent Hardware5(1), 57–67 (2023) https://doi.org/10.1016/j.vrih.2022.07.006

    work page doi:10.1016/j.vrih.2022.07.006 2023

  51. [52]

    Computer Animation and Virtual Worlds36(3), 70030 (2025) https://doi.org/10.1002/cav.70030

    Lin, C., Zou, C., Xu, H.: Scnet: A dual-branch network for strong noisy image denoising based on swin transformer and convnext. Computer Animation and Virtual Worlds36(3), 70030 (2025) https://doi.org/10.1002/cav.70030

    work page doi:10.1002/cav.70030 2025

  52. [53]

    Computer Animation and Virtual Worlds36(3), 70038 (2025) https://doi.org/10.1002/cav.70038

    Zhang, M., Zhou, J., Miao, T., Zhao, Y., Si, X., Zhang, J.: Joint-learning: A robust 19 segmentation method for 3d point clouds under label noise. Computer Animation and Virtual Worlds36(3), 70038 (2025) https://doi.org/10.1002/cav.70038

    work page doi:10.1002/cav.70038 2025

  53. [54]

    In: Proceedings of the AAAI Conference on Artificial Intelligence, vol

    Yao, L., Xu, H., Zhang, W., Liang, X., Li, Z.: Sm-nas: Structural-to-modular neural architecture search for object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12661–12668 (2020)

    work page 2020

  54. [55]

    Advances in neural information processing systems 32(2019)

    Chen, Y., Yang, T., Zhang, X., Meng, G., Xiao, X., Sun, J.: Detnas: Backbone search for object detection. Advances in neural information processing systems 32(2019)

    work page 2019

  55. [56]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Guo, J., Han, K., Wang, Y., Zhang, C., Yang, Z., Wu, H., Chen, X., Xu, C.: Hit-detector: Hierarchical trinity architecture search for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11405–11414 (2020)

    work page 2020

  56. [57]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Wang, N., Gao, Y., Chen, H., Wang, P., Tian, Z., Shen, C., Zhang, Y.: Nas- fcos: Fast neural architecture search for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11943– 11951 (2020)

    work page 2020

  57. [58]

    In: International Confer- ence on Machine Learning, pp

    Real, E., Moore, S., Selle, A., Saxena, S., Suematsu, Y.L., Tan, J., Le, Q.V., Kurakin, A.: Large-scale evolution of image classifiers. In: International Confer- ence on Machine Learning, pp. 2902–2911 (2017). PMLR

    work page 2017

  58. [59]

    arXiv preprint arXiv:1907.05737 (2019)

    Xu, Y., Xie, L., Zhang, X., Chen, X., Qi, G.-J., Tian, Q., Xiong, H.: Pc-darts: Par- tial channel connections for memory-efficient architecture search. arXiv preprint arXiv:1907.05737 (2019)

    work page arXiv 1907

  59. [60]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp

    Chen, X., Xie, L., Wu, J., Tian, Q.: Progressive differentiable architecture search: Bridging the depth gap between search and evaluation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1294–1303 (2019)

    work page 2019

  60. [61]

    arXiv preprint arXiv:2009.01027 (2020)

    Chu, X., Wang, X., Zhang, B., Lu, S., Wei, X., Yan, J.: Darts-: robustly stepping out of performance collapse without indicators. arXiv preprint arXiv:2009.01027 (2020)

    work page arXiv 2009

  61. [62]

    IEEE Transactions on Pattern Analysis and Machine Intelligence45(11), 13489– 13508 (2023) https://doi.org/10.1109/TPAMI.2023.3293885

    Chen, Z., Qiu, G., Li, P., Zhu, L., Yang, X., Sheng, B.: Mngnas: Distilling adaptive combination of multiple searched networks for one-shot neural architecture search. IEEE Transactions on Pattern Analysis and Machine Intelligence45(11), 13489– 13508 (2023) https://doi.org/10.1109/TPAMI.2023.3293885

    work page doi:10.1109/tpami.2023.3293885 2023

  62. [63]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Ghiasi, G., Lin, T.-Y., Le, Q.V.: Nas-fpn: Learning scalable feature pyramid archi- tecture for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7036–7045 (2019)

    work page 2019

  63. [64]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., Le, Q.V.: 20 Mnasnet: Platform-aware neural architecture search for mobile. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2820–2828 (2019)

    work page 2019

  64. [65]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Tan, M., Pang, R., Le, Q.V.: Efficientdet: Scalable and efficient object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10781–10790 (2020)

    work page 2020

  65. [66]

    ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

    Cai, H., Zhu, L., Han, S.: Proxylessnas: Direct neural architecture search on target task and hardware. arXiv preprint arXiv:1812.00332 (2018)

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  66. [67]

    IEEE Transactions on Multimedia25, 50–61 (2023) https://doi.org/10.1109/TMM.2021.3120873

    Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: Eapt: Efficient attention pyramid transformer for image processing. IEEE Transactions on Multimedia25, 50–61 (2023) https://doi.org/10.1109/TMM.2021.3120873

    work page doi:10.1109/tmm.2021.3120873 2023

  67. [68]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Liu, C., Chen, L.-C., Schroff, F., Adam, H., Hua, W., Yuille, A.L., Fei-Fei, L.: Auto-deeplab: Hierarchical neural architecture search for semantic image segmen- tation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 82–92 (2019)

    work page 2019

  68. [69]

    Advances in neural information processing systems33, 22158–22169 (2020)

    Cheng, X., Zhong, Y., Harandi, M., Dai, Y., Chang, X., Li, H., Drummond, T., Ge, Z.: Hierarchical neural architecture search for deep stereo matching. Advances in neural information processing systems33, 22158–22169 (2020)

    work page 2020

  69. [70]

    In: International Conference on Machine Learning, pp

    Na, B., Mok, J., Park, S., Lee, D., Choe, H., Yoon, S.: Autosnn: Towards energy-efficient spiking neural networks. In: International Conference on Machine Learning, pp. 16253–16269 (2022). PMLR

    work page 2022

  70. [71]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Qin, X., Zhang, Z., Huang, C., Gao, C., Dehghan, M., Jagersand, M.: Bas- net: Boundary-aware salient object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7479–7489 (2019)

    work page 2019

  71. [72]

    In: Proceedings of the AAAI Conference on Artificial Intelligence, vol

    Wei, J., Wang, S., Huang, Q.: F 3net: fusion, feedback and focus for salient object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12321–12328 (2020)

    work page 2020

  72. [73]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp

    Huang, Z., Zhang, Z., Lan, C., Zha, Z.-J., Lu, Y., Guo, B.: Adaptive fre- quency filters as efficient global token mixers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6049–6059 (2023)

    work page 2023

  73. [74]

    arXiv preprint arXiv:2506.18437 (2025)

    He, S., Lin, G., Li, T., Chen, Y.: Frequency-domain fusion transformer for image inpainting. arXiv preprint arXiv:2506.18437 (2025)

    work page arXiv 2025

  74. [75]

    Geng, Z., Guo, M.-H., Chen, H., Li, X., Wei, K., Lin, Z.: Is attention better than matrix decomposition? arXiv preprint arXiv:2109.04553 (2021)

    work page arXiv 2021

  75. [76]

    Segment Anything

    Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., 21 Whitehead, S., Berg, A.C., Lo, W.-Y., et al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  76. [77]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Li, A., Zhang, J., Lv, Y., Liu, B., Zhang, T., Dai, Y.: Uncertainty-aware joint salient object and camouflaged object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10071–10081 (2021)

    work page 2021

  77. [78]

    Machine Intelligence Research20(1), 92–108 (2023)

    Ji, G.-P., Fan, D.-P., Chou, Y.-C., Dai, D., Liniger, A., Van Gool, L.: Deep gra- dient learning for efficient camouflaged object detection. Machine Intelligence Research20(1), 92–108 (2023)

    work page 2023

  78. [79]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp

    Wu, Z., Paudel, D.P., Fan, D.-P., Wang, J., Wang, S., Demonceaux, C., Timofte, R., Van Gool, L.: Source-free depth for object pop-out. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1032–1042 (2023)

    work page 2023

  79. [80]

    AAAI (2023)

    He, R., Dong, Q., Lin, J., Lau, R.W.: Weakly-supervised camouflaged object detection with scribble annotations. AAAI (2023)

    work page 2023

  80. [81]

    Advances in Neural Information Processing Systems 36, 30726–30737 (2023)

    He, C., Li, K., Zhang, Y., Xu, G., Tang, L., Zhang, Y., Guo, Z., Li, X.: Weakly- supervised concealed object segmentation with sam-based pseudo labeling and multi-scale feature grouping. Advances in Neural Information Processing Systems 36, 30726–30737 (2023)

    work page 2023

Showing first 80 references.