Abstract
“Camouflage object detection(COD)” refers to identify objects hidden in the surrounding environment, such as oriental scops owl in a tree hole. Nowadays, due to the high similarity between the camouflaged object and its dependent environment, coupled with the lack of large-scale datasets, the research on this task is still very challenging. Current COD models directly send feature maps output by the backbone into the encoding-decoding module and process them equally, which may cause information interference to a certain extent. In addition, regarding the disappearance of the underlying clues in DCNNs, these models have not been well resolved. This article carries out further research based on the existing models and proposes a novel model, AGMFNet. Specifically, we introduce channel attention and spatial attention to obtain more information we need and suppress useless information to avoid information interference. In order to make feature maps integrate better, the Inception module is utilized. Furthermore, the cascade decoding module is further expanded, and we proposed a multi-level feedback module with auxiliary edge information to refine the camouflage image, which can make full use of the high-level features while retaining the low-level clues. After a series of ablation experiments on the introduced modules on the test datasets, all the combinations can improve the performance, which will also help develop camouflage object detection. The code will be available at: https://github.com/baekqiu/AGMFNet-for-COD/
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Dengping, F., Gepeng, J., Guolei, S., Mingming, C., Jianbing, S., Ling, S.: Camouflaged object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2777–2787 (2020). https://doi.org/10.1109/CVPR42600.2020.00285
Zheng, F., Xiongwei, Z., Xiaotong, D.: Camouflage people detection via strong semantic dilation network. In: ACM Turing Celebration Conference, pp. 1–7 (2019). https://doi.org/10.1145/3321408.3326662
Dong, B., Zhuge, M., Wang, Y., Bi, H., Chen, G.: Towards accurate camouflaged object detection with mixture convolution and interactive fusion. CoRR abs/2101.05687 (2021)
TsungYi, L., Piotr, D., Ross, G.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 936–944 (2017). https://doi.org/10.1109/CVPR.2017.106
Golnaz, G., TsungYi, L., Ruoming, P.: NAS-FPN: learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7036–7045 (2019). https://doi.org/10.1109/CVPR.2019.00720
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015). https://doi.org/10.1109/ICCV.2015.169
Redmon, J., Divvala, S., Girshick, R.: You only look once: unified, real time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016). https://doi.org/10.1109/CVPR.2016.91
Zhi, T., Chunhua, S., Hao, C., Tong, H.: FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9626–9635 (2019). https://doi.org/10.1109/ICCV.2019.00972
Hei, L., Jia, D.: CornerNet: detecting objects as paired keypoints. In: European Conference on Computer Vision, pp. 765–781 (2018). https://doi.org/10.1007/978-3-030-01264-9_45
Xingyi, Z., Dequan, W., Philipp, K.: Objects as points. CoRR abs/1904.07850 (2019)
Nicolas, C., Francisco, M., Gabriel, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213–229 (2020). https://doi.org/10.1007/978-3-030-58452-8_13
Boult, T., Micheals, R., Gao, X., Eckmann, M.: Into the woods: visual surveillance of noncooperative and camouflaged targets in complex outdoor settings. Proc. IEEE 89(10), 1382–1402 (2001). https://doi.org/10.1109/5.959337
Li, S., Florencio, D., Zhao, Y., Cook, C., Li, W.: Foreground detection in camouflaged scenes. In: Proceedings of the IEEE International Conference on Image Processing, pp. 4247–4251 (2017). https://doi.org/10.1109/ICIP.2017.8297083
Harville, M., Gordon, G., Woodfill, J.: Foreground segmentation using adaptive mixture models in color and depth. In: Proceedings of IEEE Workshop on Detection and Recognition of Events in Video, pp. 3–11 (2001). https://doi.org/10.1109/EVENT.2001.938860
Mondal, A., Ghosh, S., Ghosh, A.: Partially camouflaged object tracking using modified probabilistic neural network and fuzzy energy based active contour. Int. J. Comput. Vision 122(1), 116–148 (2016). https://doi.org/10.1007/s11263-016-0959-5
Yunqiu, L., Jing, Z., Yuchao, D., Aixuan, L., Bowen, L., Nick, B., et al.: Simultaneously localize, segment and rank the camouflaged objects. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11591–11601 (2021)
Skurowski, P., Abdulameer, H., Blaszczyk, J., Depta, T., Kornacki, A., Koziel, P.: Animal camouflage analysis: Chameleon database. Unpublished Manuscript (2018)
TrungNghia, L., Tam, V., Zhongliang, N., MinhTriet, T., Akihiro, S.: Anabranch network for camouflaged object segmentation, In: Computer Vision and Image Understanding, pp. 45–56 (2019). https://doi.org/10.1016/j.cviu.2019.04.006
Max, J., Karen, S., Andrew, Z., Koray.: Spatial transformer networks. In: Neural Information Processing Systems, pp. 2017–2025 (2015)
Jie, H., Li, S., Samuel, A., Gang, S., Enhua, W.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018). https://doi.org/10.1109/CVPR.2018.00745
Sanghyun, W., Jongchan, P., Joonyoung, L., So, K.: CBAM: convolutional block attention module. In: European Conference on Computer Vision, pp. 3–19 (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Xiaolong, W., Ross, B., Abhinav, G., Kaiming, H.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794–7803 (2018). https://doi.org/10.1109/CVPR.2018.00813
Hanchao, L., Pengfei, X., Jie, A., Lingxue, W.: Pyramid attention network for semantic segmentation. In: British Machine Vision Conference, pp. 285–296 (2018)
Songtao, L., Di, H., Yunhong, W.: Receptive field block net for accurate and fast object detection. In: European Conference on Computer Vision, pp. 404–419 (2018). https://doi.org/10.1007/978-3-030-01252-6_24
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 640–651 (2017). https://doi.org/10.1109/TPAMI.2016.2572683
Pingping, Z., Dong, W., Huchuan, L., Hongyu, W., Xiang, R.: Amulet: aggregating multi-level convolutional features for salient object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 202–211 (2017). https://doi.org/10.1109/ICCV.2017.31
Christian, S., Wei, L., Yangqing, J., Pierre, S., Scott, R., Dragomir, A., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015). https://doi.org/10.1109/CVPR.2015.7298594
Ran, M., Lihi, Z., Ayellet, T.: How to evaluate foreground maps. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2014). https://doi.org/10.1109/CVPR.2014.39
Dengping, F., Mingming, C., Yun, L., Tao, L., Ali, B.: Structure-measure: a new way to evaluate foreground maps. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4558–4567 (2017). https://doi.org/10.1109/ICCV.2017.487
Dengping, F., Cheng, G., Yang, C., Bo, R., Mingming, C., Ali, B.: Enhanced-alignment measure for binary foreground map evaluation. In: Proceedings of the International Joint Conference on Artificial Intelligence, pp. 698–704 (2018). https://doi.org/10.24963/ijcai.2018/97
Kaiming, H., Georgia, G., Piotr, D., Ross, G.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017). https://doi.org/10.1109/ICCV.2017.322
Zhou, Z., Rahman, S., Tajbakhsh, N., Liang, J.: UNet++: a nested UNet architecture for medical image segmentation. In: Deep Learning on Medical Image Analysis, pp. 3–11 (2018). https://doi.org/10.1007/978-3-030-00889-5_1
Zhaojin, H., Lichao, H., Yongchao, G., Chang, H., Xinggang, W.: Mask scoring R-CNN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6409–6418 (2019). https://doi.org/10.1109/CVPR.2019.00657
Ting, Z., Xiangqian, W.: Pyramid feature attention network for saliency detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3085–3094 (2019). https://doi.org/10.1109/CVPR.2019.00320
Jiaxing, Z., Jiangjiang, L., Dengping, F., Yang, C., Jufeng, Y., Mingming, C.: EGNet: edge guidance network for salient object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8778–8787 (2019). https://doi.org/10.1109/ICCV.2019.00887
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Tang, Q., Ye, J., Chen, F., Yuan, X. (2022). Attention Guided Multi-level Feedback Network for Camouflage Object Detection. In: Wallraven, C., Liu, Q., Nagahara, H. (eds) Pattern Recognition. ACPR 2021. Lecture Notes in Computer Science, vol 13188. Springer, Cham. https://doi.org/10.1007/978-3-031-02375-0_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-02375-0_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-02374-3
Online ISBN: 978-3-031-02375-0
eBook Packages: Computer ScienceComputer Science (R0)