Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation (2304.07444v4)

Published 15 Apr 2023 in cs.CV

Abstract: Camouflaged object detection and segmentation is a new and challenging research topic in computer vision. There is a serious issue of lacking data on concealed objects such as camouflaged animals in natural scenes. In this paper, we address the problem of few-shot learning for camouflaged object detection and segmentation. To this end, we first collect a new dataset, CAMO-FS, for the benchmark. As camouflaged instances are challenging to recognize due to their similarity compared to the surroundings, we guide our models to obtain camouflaged features that highly distinguish the instances from the background. In this work, we propose FS-CDIS, a framework to efficiently detect and segment camouflaged instances via two loss functions contributing to the training process. Firstly, the instance triplet loss with the characteristic of differentiating the anchor, which is the mean of all camouflaged foreground points, and the background points are employed to work at the instance level. Secondly, to consolidate the generalization at the class level, we present instance memory storage with the scope of storing camouflaged features of the same category, allowing the model to capture further class-level information during the learning process. The extensive experiments demonstrated that our proposed method achieves state-of-the-art performance on the newly collected dataset. Code is available at https://github.com/danhntd/FS-CDIS.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (75)
  1. S. Singh, C. Dhawale, and S. Misra, “Survey of object detection methods in camouflaged image,” IERI Procedia, vol. 4, pp. 351 – 357, 2013.
  2. T.-N. Le, T. V. Nguyen, Z. Nie, M.-T. Tran, and A. Sugimoto, “Anabranch network for camouflaged object segmentation,” CVIU, vol. 184, pp. 45–56, 2019.
  3. T.-N. Le, H. H. Nguyen, J. Yamagishi, and I. Echizen, “Openforensics: Large-scale challenging dataset for multi-face forgery detection and segmentation in-the-wild,” in ICCV, 2021.
  4. C. Kervrann and F. Heitz, “A markov random field model-based approach to unsupervised texture segmentation using local and global spatial statistics,” IEEE TIP, vol. 4, no. 6, pp. 856–862, 1995.
  5. Y. Boykov and G. Funka-Lea, “Graph cuts and efficient nd image segmentation,” IJCV, vol. 70, no. 2, pp. 109–131, 2006.
  6. X. Li and H. Sahbi, “Superpixel-based object class segmentation using conditional random fields,” in ICASSP, 2011, pp. 1101–1104.
  7. L. Sulimowicz, I. Ahmad, and A. Aved, “Superpixel-enhanced pairwise conditional random field for semantic segmentation,” in ICIP, 2018, pp. 271–275.
  8. M. Galun, E. Sharon, R. Basri, and A. Brandt, “Texture segmentation by multiscale aggregation of filter responses and shape elements,” in ICCV, Oct 2003, pp. 716–723.
  9. L. Song and W. Geng, “A new camouflage texture evaluation method based on wssim and nature image features,” in International Conference on Multimedia Technology, Oct 2010, pp. 1–4.
  10. F. Xue, C. Yong, S. Xu, H. Dong, Y. Luo, and W. Jia, “Camouflage performance analysis and evaluation framework based on features fusion,” Multimedia Tools and Applications, vol. 75, pp. 4065–4082, 2016.
  11. Y. Pan, Y. Chen, Q. Fu, P. Zhang, and X. Xu, “Study on the camouflaged target detection method based on 3d convexity,” Modern Applied Science, vol. 5, no. 4, p. 152, 2011.
  12. Z. Liu, K. Huang, and T. Tan, “Foreground object detection using top-down information based on em framework,” IEEE TIP, vol. 21, no. 9, pp. 4204–4217, Sept 2012.
  13. A. W. P. Sengottuvelan and A. Shanmugam, “Performance of decamouflaging through exploratory image analysis,” in ICETET, 2008, pp. 6–10.
  14. J. Yin, Y. Han, W. Hou, and J. Li, “Detection of the mobile object with camouflage color under dynamic background based on optical flow,” Procedia Engineering, vol. 15, pp. 2201 – 2205, 2011.
  15. J. Gallego and P. Bertolino, “Foreground object segmentation for moving camera sequences based on foreground-background probabilistic models and prior probability maps,” in ICIP, Oct 2014, pp. 3312–3316.
  16. D.-P. Fan, G.-P. Ji, G. Sun, M.-M. Cheng, J. Shen, and L. Shao, “Camouflaged object detection,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 2777–2787.
  17. E. L.-M. Pia Bideau, “It’s moving! a probabilistic model for causal motion segmentation in moving camera videos,” in ECCV, 2016.
  18. H. Lamdouar, C. Yang, W. Xie, and A. Zisserman, “Betrayed by motion: Camouflaged object discovery via motion segmentation,” in ACCV, November 2020.
  19. P. Skurowski, H. Abdulameer, J. Baszczyk, T. Depta, A. Kornacki, and P. Kozie, “Animal camouflage analysis: Chameleon database,” Unpublished Manuscript, 2018.
  20. Y. Lv, J. Zhang, Y. Dai, A. Li, B. Liu, N. Barnes, and D.-P. Fan, “Simultaneously localize, segment and rank the camouflaged objects,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 11 591–11 601.
  21. T.-N. Le, Y. Cao, T.-C. Nguyen, M.-Q. Le, K.-D. Nguyen, T.-T. Do, M.-T. Tran, and T. V. Nguyen, “Camouflaged instance segmentation in-the-wild: Dataset, method, and benchmark suite,” IEEE Transactions on Image Processing, vol. 31, pp. 287–300, 2022.
  22. L. Song and W. Geng, “A new camouflage texture evaluation method based on wssim and nature image features,” in 2010 International Conference on Multimedia Technology.   IEEE, 2010, pp. 1–4.
  23. P. Siricharoen, S. Aramvith, T. Chalidabhongse, and S. Siddhichai, “Robust outdoor human segmentation based on color-based statistical approach and edge combination,” in The 2010 International Conference on Green Circuits and Systems.   IEEE, 2010, pp. 463–468.
  24. M. Galun, E. Sharon, R. Basri, and A. Brandt, “Texture segmentation by multiscale aggregation of filter responses and shape elements.” in ICCV, vol. 3, 2003, p. 716.
  25. C. Kavitha, B. P. Rao, and A. Govardhan, “An efficient content based image retrieval using color and texture of image sub-blocks,” International Journal of Engineering Science and Technology (IJEST), vol. 3, no. 2, pp. 1060–1068, 2011.
  26. F. Xue, C. Yong, S. Xu, H. Dong, Y. Luo, and W. Jia, “Camouflage performance analysis and evaluation framework based on features fusion,” Multimedia Tools and Applications, vol. 75, no. 7, pp. 4065–4082, 2016.
  27. J. Y. Y. H. W. Hou and J. Li, “Detection of the mobile object with camouflage color under dynamic background based on optical flow,” Procedia Engineering, vol. 15, pp. 2201–2205, 2011.
  28. Q. Zhai, X. Li, F. Yang, C. Chen, H. Cheng, and D.-P. Fan, “Mutual graph learning for camouflaged object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 12 997–13 007.
  29. A. Li, J. Zhang, Y. Lv, B. Liu, T. Zhang, and Y. Dai, “Uncertainty-aware joint salient object and camouflaged object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 10 071–10 081.
  30. H. Mei, G.-P. Ji, Z. Wei, X. Yang, X. Wei, and D.-P. Fan, “Camouflaged object segmentation with distraction mining,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 8772–8781.
  31. J. Yan, T.-N. Le, K.-D. Nguyen, M.-T. Tran, T.-T. Do, and T. V. Nguyen, “Mirrornet: Bio-inspired camouflaged object segmentation,” IEEE Access, vol. 9, pp. 43 290–43 300, 2021.
  32. J. Zhu, X. Zhang, S. Zhang, and J. Liu, “Inferring camouflage objects by texture-aware interactive guidance network,” in AAAI, 2021.
  33. N. Price, S. Green, J. Troscianko, T. Tregenza, and M. Stevens, “Background matching and disruptive coloration as habitat-specific strategies for camouflage,” Scientific reports, vol. 9, no. 1, pp. 1–10, 2019.
  34. T.-N. Le, V. Nguyen, C. Le, T.-C. Nguyen, M.-T. Tran, and T. V. Nguyen, “Camoufinder: Finding camouflaged instances in images,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 18, 2021, pp. 16 071–16 074.
  35. Q. Fan, W. Zhuo, C.-K. Tang, and Y.-W. Tai, “Few-shot object detection with attention-rpn and multi-relation detector,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
  36. B. Kang, Z. Liu, X. Wang, F. Yu, J. Feng, and T. Darrell, “Few-shot object detection via feature reweighting,” in ICCV, 2019.
  37. X. Wang, T. E. Huang, T. Darrell, J. E. Gonzalez, and F. Yu, “Frustratingly simple few-shot object detection,” in ICML, 2020.
  38. X. Yan, Z. Chen, A. Xu, X. Wang, X. Liang, and L. Lin, “Meta r-cnn: Towards general solver for instance-level low-shot learning,” in ICCV, 2019.
  39. J. Redmon and A. Farhadi, “Yolo9000: better, faster, stronger,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 7263–7271.
  40. K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask r-cnn,” in ICCV, 2017, pp. 2980–2988.
  41. B. Li, B. Yang, C. Liu, F. Liu, R. Ji, and Q. Ye, “Beyond max-margin: Class margin equilibrium for few-shot object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
  42. H. Hu, S. Bai, A. Li, J. Cui, and L. Wang, “Dense relation distillation with context-aware aggregation for few-shot object detection,” in Proceedings of (CVPR), 2021.
  43. Y. Xiao and R. Marlet, “Few-shot object detection and viewpoint estimation for objects in the wild,” in European conference on computer vision.   Springer, 2020, pp. 192–210.
  44. G. Han, Y. He, S. Huang, J. Ma, and S.-F. Chang, “Query adaptive few-shot object detection with heterogeneous graph convolutional networks,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 3263–3272.
  45. G. Han, S. Huang, J. Ma, Y. He, and S.-F. Chang, “Meta faster r-cnn: Towards accurate few-shot object detection with attentive feature alignment,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 1, 2022, pp. 780–789.
  46. A. Li and Z. Li, “Transformation invariant few-shot object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
  47. J. Wu, S. Liu, D. Huang, and Y. Wang, “Multi-scale positive sample refinement for few-shot object detection,” in ECCV, 2020.
  48. G. Zhang, Z. Luo, K. Cui, and S. Lu, “Meta-detr: Image-level few-shot object detection with inter-class correlation exploitation,” arXiv preprint arXiv:2103.11731, 2021.
  49. G. Han, J. Ma, S. Huang, L. Chen, and S.-F. Chang, “Few-shot object detection with fully cross-transformer,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5321–5330.
  50. B. Sun, B. Li, S. Cai, Y. Yuan, and C. Zhang, “Fsce: Few-shot object detection via contrastive proposal encoding,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 7352–7362.
  51. S. Zhang, L. Wang, N. Murray, and P. Koniusz, “Kernelized few-shot object detection with efficient integral aggregation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 19 207–19 216.
  52. L. Qiao, Y. Zhao, Z. Li, X. Qiu, J. Wu, and C. Zhang, “Defrcn: Decoupled faster r-cnn for few-shot object detection,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 8681–8690.
  53. W. Zhang and Y.-X. Wang, “Hallucination improves few-shot object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 13 008–13 017.
  54. C. Zhu, F. Chen, U. Ahmed, Z. Shen, and M. Savvides, “Semantic relation reasoning for shot-stable few-shot object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
  55. S. Khandelwal, R. Goyal, and L. Sigal, “Unit: Unified knowledge transfer for any-shot object detection and segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
  56. W. Liu, C. Zhang, G. Lin, and F. Liu, “Crnet: Cross-reference networks for few-shot segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020.
  57. N. Dong and E. P. Xing, “Few-shot semantic segmentation with prototype learning.” in BMVC, vol. 3, no. 4, 2018.
  58. K. Wang, J. H. Liew, Y. Zou, D. Zhou, and J. Feng, “Panet: Few-shot image semantic segmentation with prototype alignment,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2019.
  59. O. Saha, Z. Cheng, and S. Maji, “Ganorcon: Are generative models useful for few-shot segmentation?” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2022, pp. 9991–10 000.
  60. Z. Tian, X. Lai, L. Jiang, S. Liu, M. Shu, H. Zhao, and J. Jia, “Generalized few-shot semantic segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2022, pp. 11 563–11 572.
  61. K. Nguyen and S. Todorovic, “ifs-rcnn: An incremental few-shot instance segmenter,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 7010–7019.
  62. B.-B. Gao, X. Chen, Z. Huang, C. Nie, J. Liu, J. Lai, G. Jiang, X. Wang, and C. Wang, “Decoupling classifier for boosting few-shot object detection and instance segmentation,” in NeurIPS 2022, 2022.
  63. Y. Han, J. Zhang, Z. Xue, C. Xu, X. Shen, Y. Wang, C. Wang, Y. Liu, and X. Li, “Reference twice: A simple and unified baseline for few-shot instance segmentation,” arXiv preprint arXiv:2301.01156, 2023.
  64. H. Wang, J. Liu, Y. Liu, S. Maji, J.-J. Sonke, and E. Gavves, “Dynamic transformer for few-shot instance segmentation,” in Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 2969–2977.
  65. J. Snell, K. Swersky, and R. Zemel, “Prototypical networks for few-shot learning,” Advances in neural information processing systems, vol. 30, 2017.
  66. O. Vinyals, C. Blundell, T. Lillicrap, D. Wierstra et al., “Matching networks for one shot learning,” Advances in neural information processing systems, vol. 29, 2016.
  67. S. Gidaris and N. Komodakis, “Dynamic few-shot visual learning without forgetting,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 4367–4375.
  68. Z. Fan, J.-G. Yu, Z. Liang, J. Ou, C. Gao, G.-S. Xia, and Y. Li, “Fgn: Fully guided network for few-shot instance segmentation,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 9172–9181.
  69. S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,” in NeurIPS, 2015, pp. 91–99.
  70. D. A. Ganea, B. Boom, and R. Poppe, “Incremental few-shot instance segmentation,” in Proceedings of (CVPR), June 2021, pp. 1185–1194.
  71. V. Balntas, E. Riba, D. Ponsa, and K. Mikolajczyk, “Learning local feature descriptors with triplets and shallow convolutional neural networks.” in Bmvc, vol. 1, no. 2, 2016, p. 3.
  72. Z. Wu, Y. Xiong, S. X. Yu, and D. Lin, “Unsupervised feature learning via non-parametric instance discrimination,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 3733–3742.
  73. Y. Wu, A. Kirillov, F. Massa, W.-Y. Lo, and R. Girshick, “Detectron2,” https://github.com/facebookresearch/detectron2, 2019.
  74. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in CVPR, 2016.
  75. T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature pyramid networks for object detection,” in CVPR, 2017.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (8)
  1. Thanh-Danh Nguyen (1 paper)
  2. Anh-Khoa Nguyen Vu (4 papers)
  3. Nhat-Duy Nguyen (2 papers)
  4. Vinh-Tiep Nguyen (12 papers)
  5. Thanh Duc Ngo (4 papers)
  6. Thanh-Toan Do (92 papers)
  7. Minh-Triet Tran (72 papers)
  8. Tam V. Nguyen (40 papers)
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now