Papers
Topics
Authors
Recent
Search
2000 character limit reached

Shifting Spotlight for Co-supervision: A Simple yet Efficient Single-branch Network to See Through Camouflage

Published 13 Apr 2024 in cs.CV | (2404.08936v2)

Abstract: Camouflaged object detection (COD) remains a challenging task in computer vision. Existing methods often resort to additional branches for edge supervision, incurring substantial computational costs. To address this, we propose the Co-Supervised Spotlight Shifting Network (CS$3$Net), a compact single-branch framework inspired by how shifting light source exposes camouflage. Our spotlight shifting strategy replaces multi-branch designs by generating supervisory signals that highlight boundary cues. Within CS$3$Net, a Projection Aware Attention (PAA) module is devised to strengthen feature extraction, while the Extended Neighbor Connection Decoder (ENCD) enhances final predictions. Extensive experiments on public datasets demonstrate that CS$3$Net not only achieves superior performance, but also reduces Multiply-Accumulate operations (MACs) by 32.13% compared to state-of-the-art COD methods, striking an optimal balance between efficiency and effectiveness.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (69)
  1. Improving unsupervised defect segmentation by applying structural similarity to autoencoders. arXiv preprint arXiv:1807.02011 (2018).
  2. Cuttlefish adjust body pattern intensity with respect to substrate intensity to aid camouflage, but do not camouflage in extremely low light. Journal of Experimental Marine Biology and Ecology 462 (2015), 121–126.
  3. Camouflaged object detection via context-aware cross-level fusion. IEEE TCSVT 32, 10 (2022), 6981–6993.
  4. Pedestrian attribute recognition in video surveillance scenarios based on view-attribute attention localization. Machine Intelligence Research 19, 2 (2022), 153–168.
  5. Diffusion model for camouflaged object detection. arXiv preprint arXiv:2308.00303 (2023).
  6. Hyperspectral imaging of cuttlefish camouflage indicates good color match in the eyes of fish predators. Proceedings of the National Academy of Sciences 108, 22 (2011), 9148–9153.
  7. Camouflage in a dynamic world. Current Opinion in Behavioral Sciences 30 (2019), 109–115.
  8. Structure-measure: A new way to evaluate foreground maps. In ICCV. 4548–4557.
  9. Concealed object detection. IEEE transactions on pattern analysis and machine intelligence 44, 10 (2021), 6024–6042.
  10. Cognitive vision inspired object segmentation metric and loss function. Scientia Sinica Informationis 6, 6 (2021).
  11. Camouflaged Object Detection. In CVPR.
  12. Pranet: Parallel reverse attention network for polyp segmentation. In MICCAI. Springer, 263–273.
  13. Inf-net: Automatic covid-19 lung infection segmentation from ct images. IEEE TMI 39, 8 (2020), 2626–2637.
  14. Finding a signal hidden among noise: how can predators overcome camouflage strategies? Philosophical Transactions of the Royal Society B 375, 1802 (2020), 20190478.
  15. Highly efficient salient object detection with 100k parameters. In ECCV. Springer, 702–721.
  16. Deep sparse rectifier neural networks. In AISTATS. JMLR Workshop and Conference Proceedings, 315–323.
  17. Camouflaged object detection with feature decomposition and edge reconstruction. In CVPR. 22046–22055.
  18. Weakly-supervised concealed object segmentation with sam-based pseudo labeling and multi-scale feature grouping. NIPS 36 (2024).
  19. Weakly-supervised camouflaged object detection with scribble annotations. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37. 781–789.
  20. Jianqin Yin Yanbin Han Wendi Hou and Jinping Li. 2011. Detection of the mobile object with camouflage color under dynamic background based on optical flow. Procedia Engineering 15 (2011), 2201–2205.
  21. High-resolution iterative feedback network for camouflaged object detection. In AAAI, Vol. 37. 881–889.
  22. Feature shrinkage pyramid for camouflaged object detection with transformers. In CVPR. 5557–5566.
  23. Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML. pmlr, 448–456.
  24. Progressively normalized self-attention network for video polyp segmentation. In MICCAI. Springer, 142–152.
  25. Deep Gradient Learning for Efficient Camouflaged Object Detection. Machine Intelligence Research 20 (2023), 92–108. Issue 1.
  26. Video polyp segmentation: A deep learning perspective. Machine Intelligence Research 19, 6 (2022), 531–549.
  27. Fast camouflaged object detection via edge-based reversible re-calibration network. PR 123 (2022), 108414.
  28. Sungho Kim et al. 2015. Unsupervised spectral-spatial feature selection-based camouflaged object detection using VNIR hyperspectral camera. The Scientific World Journal 2015 (2015).
  29. Imagenet classification with deep convolutional neural networks. NeurIPS 25 (2012).
  30. Anabranch network for camouflaged object segmentation. Computer Vision and Image Understanding 184 (2019), 45–56.
  31. Uncertainty-aware joint salient object and camouflaged object detection. In CVPR. 10071–10081.
  32. COVID-19 lung infection segmentation with a novel two-stage cross-domain transfer learning framework. Medical Image Analysis 74 (2021), 102205.
  33. Explicit visual prompting for low-level structure segmentations. In CVPR. 19434–19445.
  34. Bi-RRNet: Bi-level recurrent refinement network for camouflaged object detection. Pattern Recognition 139 (2023), 109514.
  35. Simultaneously Localize, Segment and Rank the Camouflaged Objects. In CVPR. 11591–11601.
  36. Simultaneously localize, segment and rank the camouflaged objects. In CVPR. 11591–11601.
  37. How to evaluate foreground maps?. In CVPR. 248–255.
  38. Camouflaged object segmentation with distraction mining. In CVPR. 8772–8781.
  39. Distraction-aware camouflaged object segmentation. SCIENTIA SINICA Informationis (SSI) 3 (2023), 7.
  40. Study on the camouflaged target detection method based on 3D convexity. Modern Applied Science 5, 4 (2011), 152.
  41. Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection. In CVPR.
  42. Matilda QR Pembury Smith and Graeme D Ruxton. 2020. Camouflage in predators. Biological Reviews 95, 5 (2020), 1325–1340.
  43. Boundary-aware segmentation network for mobile and web applications. arXiv preprint arXiv:2101.04704 (2021).
  44. Craig Reynolds. 2011. Interactive evolution of camouflage. Artificial life 17, 2 (2011), 123–136.
  45. Martin Stevens and Sami Merilaita. 2009. Animal camouflage: current issues and new perspectives. Philosophical Transactions of the Royal Society B: Biological Sciences 364, 1516 (2009), 423–427.
  46. Edge-Aware Mirror Network for Camouflaged Object Detection. In ICME. IEEE, 2465–2470.
  47. Context-aware Cross-level Fusion Network for Camouflaged Object Detection. In IJCAI. 1025–1031.
  48. Segmentation-based deep-learning approach for surface-defect detection. Journal of Intelligent Manufacturing 31, 3 (2020), 759–776.
  49. Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In ICML. PMLR, 6105–6114.
  50. Auto-annotated deep segmentation for surface defect detection. IEEE Transactions on Instrumentation and Measurement 70 (2021), 1–10.
  51. Depth-aided Camouflaged Object Detection. In Proceedings of the 31st ACM International Conference on Multimedia. 3297–3306.
  52. Pvtv2: Improved baselines with pyramid vision transformer. Computational Visual Media 8, 3 (2022), 1–10.
  53. F33{}^{3}start_FLOATSUPERSCRIPT 3 end_FLOATSUPERSCRIPTNet: fusion, feedback and focus for salient object detection. In AAAI, Vol. 34. 12321–12328.
  54. A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision. In CVPR.
  55. Jcs: An explainable covid-19 diagnosis system by joint classification and segmentation. IEEE TIP 30 (2021), 3113–3126.
  56. Cascaded partial decoder for fast and accurate salient object detection. In CVPR. 3907–3916.
  57. Stacked Cross Refinement Network for Edge-Aware Salient Object Detection. In ICCV.
  58. Frequency representation integration for camouflaged object detection. In Proceedings of the 31st ACM International Conference on Multimedia. 1789–1797.
  59. Uncertainty-guided transformer reasoning for camouflaged object detection. In ICCV. 4146–4155.
  60. Restormer: Efficient transformer for high-resolution image restoration. In CVPR. 5728–5739.
  61. Mutual graph learning for camouflaged object detection. In CVPR. 12997–13007.
  62. Preynet: Preying on camouflaged objects. In ACM MM. 5323–5332.
  63. TPRNet: camouflaged object detection via transformer-induced progressive refinement network. TVCJ (2022), 1–15.
  64. EGNet: Edge guidance network for salient object detection. In ICCV. 8779–8788.
  65. Detecting camouflaged object in frequency domain. In CVPR. 4504–4513.
  66. Interactive two-stream decoder for accurate and fast saliency detection. In CVPR. 9141–9150.
  67. Feature aggregation and propagation network for camouflaged object detection. IEEE TIP 31 (2022), 7036–7047.
  68. I can find you! boundary-guided separated attention network for camouflaged object detection. In AAAI, Vol. 36. 3608–3616.
  69. Inferring camouflaged objects by texture-aware interactive guidance network. In AAAI, Vol. 35. 3599–3607.
Citations (1)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

Sign Up for Free