{"type":"ScholarlyArticle","title":"Boundary-Guided Camouflaged Object Detection","authors":[{"name":"Yujia Sun","slug":"yujia-sun","given":"Yujia","family":"Sun","affiliation":"School of Computer Science , Inner Mongolia University , China"},{"name":"Shuo Wang","slug":"shuo-wang","given":"Shuo","family":"Wang","affiliation":"ETH Zurich , Switzerland"},{"name":"Chenglizhao Chen","slug":"chenglizhao-chen","given":"Chenglizhao","family":"Chen","affiliation":"College of Computer Science and Technology , China University of Petroleum , China"},{"name":"Tian-Zhu Xiang","slug":"tian-zhu-xiang","given":"Tian-Zhu","family":"Xiang","affiliation":"Inception Institute of Artificial Intelligence , UAE"}],"abstract":"Camouflaged object detection (COD), segmenting objects that are elegantly blended into their surroundings, is a valuable yet challenging task. Existing deep-learning methods often fall into the difficulty of accurately identifying the camouflaged object with complete and fine object structure. To this end, in this paper, we propose a novel boundary-guided network (BGNet) for camouflaged object detection. Our method explores valuable and extra object-related edge semantics to guide representation learning of COD, which forces the model to generate features that highlight object structure, thereby promoting camouflaged object detection of accurate boundary localization. Extensive experiments on three challenging benchmark datasets demonstrate that our BGNet significantly outperforms the existing 18 state-of-the-art methods under four widely-used evaluation metrics. Our code is publicly available at: https://github.com/thograce/BGNet.","doi":"10.24963/ijcai.2022/186","url":"https://ijcai.org/proceedings/2022/186","pdf":"https://ijcai.org/proceedings/2022/0186.pdf","markdown":"https://ijcai.org/proceedings/2022/186.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/186","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Computer Vision","track":"Main Track","number":186,"pages":{"first":1335,"last":1341},"keywords":["Computer Vision: Recognition (object detection, categorization)","Computer Vision: Segmentation"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986499","length_sec":81,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984642","length_sec":338,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Cheng et al., 2022] X Cheng, H Xiong, D-P Fan, Y Zhong, and et al. Implicit motion handling for video camouflaged object detection. In CVPR, 2022.","title":"Implicit motion handling for video camouflaged object detection","authors":"Cheng","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Fan et al., 2017] D-P Fan, M-M Cheng, Y Liu, T Li, and A Borji. Structre-measure: A new way to evaluate fore- ground maps. In ICCV, 2017.","title":"Structre-measure: A new way to evaluate foreground maps","authors":"D-P Fan, M-M Cheng, Y Liu, T Li, Borji","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Fan et al., 2020a] D-P Fan, G-P Ji, G Sun, M-M Cheng, J Shen, and L Shao. Camouflaged object detection. In CVPR, 2020.","title":"Camouflaged object detection","authors":"Fan","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Fan et al., 2020b] D-P Fan, G-P Ji, T Zhou, G Chen, H-Z Fu, J-B Shen, and L Shao. Pranet: Parallel reverse atten- tion network for polyp segmentation. In MICCAI, 2020.","title":"Pranet: Parallel reverse attention network for polyp segmentation","authors":"Fan","year":"2020","venue":"MICCAI","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Fan et al., 2020c] D-P Fan, Y Zhai, A Borji, and et al. Bbs- net: Rgb-d salient object detection with a bifurcated back- bone strategy network. In ECCV, 2020.","title":"Bbsnet: Rgb-d salient object detection with a bifurcated backbone strategy network","authors":"Fan","year":"2020","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Fan et al., 2021a] D-P Fan, G-P Ji, M-M Cheng, and L Shao. Concealed object detection. IEEE TPAMI, 2021.","title":"Concealed object detection","authors":"Fan","year":"2021","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Fan et al., 2021b] D-P Fan, G-P Ji, X Qin, and M-M Cheng. Cognitive vision inspired object segmentation metric and loss function. In SSI, 2021.","title":"Cognitive vision inspired object segmentation metric and loss function","authors":"Fan","year":"2021","venue":"SSI","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gao et al., 2019] S Gao, M Cheng, K Zhao, X Zhang, M Yang, and P Torr. Res2net: A new multi-scale back- bone architecture. IEEE TPAMI, 2019.","title":"Res2net: A new multi-scale backbone architecture","authors":"M Gao, K Cheng, X Zhao, M Zhang, Yang, Torr","year":"2019","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gao et al., 2020] S Gao, Y Tan, M-M Cheng, C Lu, Y Chen, and S Yan. Highly efficient salient object detection with 100k parameters. In ECCV, 2020.","title":"Highly efficient salient object detection with 100k parameters","authors":"Gao, M-M Tan, C Cheng, Y Lu, Chen, Yan","year":"2020","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kingma and Ba, 2014] D P Kingma and J Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"D P Kingma, J Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Le et al., 2019] T-N Le, T V Nguyen, Z Nie, M-T Tran, and A Sugimoto. Anabranch network for camouflaged object segmentation. CVIU, 2019.","title":"Anabranch network for camouflaged object segmentation","authors":"T-N Le, T V Nguyen, Z Nie, M-T Tran, Sugimoto","year":"2019","venue":"CVIU","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2021] A Li, J Zhang, Y Lv, B Liu, T Zhang, and Y Dai. Uncertainty-aware joint salient object and camou- flaged object detection. In CVPR, 2021.","title":"Uncertainty-aware joint salient object and camouflaged object detection","authors":"J Li, Y Zhang, B Lv, T Liu, Y Zhang, Dai","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu et al., 2019] J-J Liu, Q Hou, M-M Cheng, J Feng, and J Jiang. A simple pooling-based design for real-time salient object detection. In CVPR, 2019.","title":"A simple pooling-based design for real-time salient object detection","authors":"J-J Liu, Q Hou, M-M Cheng, J Feng, Jiang","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Lv et al., 2021] Y Lv, J Zhang, Y Dai, A Li, B Liu, N Barnes, and D Fan. Simultaneously localize, segment and rank the camouflaged objects. In CVPR, 2021.","title":"Simultaneously localize, segment and rank the camouflaged objects","authors":"Lv, Y Zhang, Dai, B Li, N Liu, Barnes, Fan","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Margolin et al., 2014] R Margolin, L Zelnik-Manor, and A Tal. How to evaluate foreground maps? In CVPR, 2014.","title":"How to evaluate foreground maps?","authors":"L Margolin, Zelnik-Manor","year":"2014","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Mei et al., 2021] H Mei, G Ji, Z Wei, X Wei X Yang, and D Fan. Camouflaged object segmentation with distraction mining. In CVPR, 2021.","title":"Camouflaged object segmentation with distraction mining","authors":"G Mei, Z Ji, X Wei, Wei X Yang, Fan","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Pang et al., 2020] Y Pang, X Zhao, L Zhang, and H Lu. Multi-scale interactive network for salient object detec- tion. In CVPR, 2020.","title":"Multi-scale interactive network for salient object detection","authors":"Pang, L Zhao, H Zhang, Lu","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Pang et al., 2022] Y Pang, X Zhao, T-Z Xiang, L Zhang, and H Lu. Zoom in and out: A mixed-scale triplet net- work for camouflaged object detection. In CVPR, 2022.","title":"Zoom in and out: A mixed-scale triplet network for camouflaged object detection","authors":"Pang, T-Z Zhao, L Xiang, H Zhang, Lu","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Perazzi et al., 2012] F Perazzi, P Krähenbühl, Y Pritch, and A Hornung. Saliency filters: Contrast based filtering for salient region detection. In CVPR, 2012.","title":"Saliency filters: Contrast based filtering for salient region detection","authors":"Perazzi, Y Krähenbühl, Pritch, Hornung","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Price et al., 2019] N Price, S Green, J Troscianko, T Tre- genza, and M Stevens. Background matching and dis- ruptive coloration as habitat-specific strategies for camou- flage. Scientific reports, 9(1):1-10, 2019.","title":"Background matching and disruptive coloration as habitat-specific strategies for camouflage","authors":"Price, J Green, T Troscianko, M Tregenza, Stevens","year":"2019","venue":"Scientific reports","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Qin et al., 2021] X-B Qin, D-P Fan, C-Y Huang, and et al. Boundary-aware segmentation network for mobile and web applications. arXiv preprint arXiv:2101.04704, 2021.","title":"Boundary-aware segmentation network for mobile and web applications","authors":"X-B Qin, D-P Fan, C-Y Huang","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Ricardo et al., 2012] P F Ricardo, X Delclòs, E Peñalver, and et al. Early evolution and ecology of camouflage in insects. PNAS, 109(52):21414-21419, 2012.","title":"Early evolution and ecology of camouflage in insects","authors":"X P F Ricardo, E Delclòs, Peñalver","year":"2012","venue":"PNAS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Stevens et al., 2009] Martin Stevens, Sami Merilaita, et al. Animal camouflage: current issues and new perspectives. RSTB, 364(1516):423-427, 2009.","title":"Animal camouflage: current issues and new perspectives","authors":"Martin Stevens, Sami Merilaita","year":"2009","venue":"RSTB","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Sun et al., 2021] Y Sun, G Chen, T Zhou, Y Zhang, and N Liu. Context-aware cross-level fusion network for cam- ouflaged object detection. In IJCAI, 2021.","title":"Context-aware cross-level fusion network for camouflaged object detection","authors":"Sun, T Chen, Y Zhou, Zhang, Liu","year":"2021","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2021/142"},{"position":25,"raw":"[Wang et al., 2020] Q Wang, B Wu, P Zhu, P Li, W Zuo, and Q Hu. Eca-net: Efficient channel attention for deep convolutional neural networks. In CVPR, 2020.","title":"Eca-net: Efficient channel attention for deep convolutional neural networks","authors":"B Wang, P Wu, P Zhu, W Li, Zuo, Hu","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wei et al., 2020] Jun Wei, Shuhui Wang, and Qingming Huang. F 3 net: Fusion, feedback and focus for salient ob- ject detection. In AAAI, 2020.","title":"F 3 net: Fusion, feedback and focus for salient object detection","authors":"Jun Wei, Shuhui Wang, Qingming Huang","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wu et al., 2019] Zhe Wu, Li Su, and Qingming Huang. Stacked cross refinement network for edge-aware salient object detection. In CVPR, 2019.","title":"Stacked cross refinement network for edge-aware salient object detection","authors":"Zhe Wu, Li Su, Qingming Huang","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Wu et al., 2020] Y Wu, Y Liu, L Zhang, and et al. EDN: Salient object detection via extremely-downsampled net- work. arXiv preprint arXiv:2012.13093, 2020.","title":"EDN: Salient object detection via extremely-downsampled network","authors":"Y Wu, L Liu, Zhang","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Xie et al., 2020] Enze Xie, Wenjia Wang, Wenhai Wang, Mingyu Ding, Chunhua Shen, and Ping Luo. Segmenting transparent objects in the wild. In ECCV, 2020.","title":"Segmenting transparent objects in the wild","authors":"Xie","year":"2020","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Yan et al., 2021] J Yan, T-N Le, K-D Nguyen, M-T Tran, and T-T Do. Mirrornet: Bio-inspired camouflaged object segmentation. IEEE Access, 9:43290-43300, 2021.","title":"Mirrornet: Bio-inspired camouflaged object segmentation","authors":"T-N Yan, K-D Le, M-T Nguyen, T-T Tran, Do","year":"2021","venue":"IEEE Access","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Yang et al., 2021] F Yang, Q Zhai, X Li, R Huang, A Luo, H Cheng, and D Fan. Uncertainty-guided transformer rea- soning for camouflaged object detection. In ICCV, 2021.","title":"Uncertainty-guided transformer reasoning for camouflaged object detection","authors":"Q Yang, X Zhai, R Li, Huang, H Luo, Cheng, Fan","year":"2021","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhai et al., 2021] Q Zhai, X Li, F Yang, C Chen, H Cheng, and D Fan. Mutual graph learning for camouflaged object detection. In CVPR, 2021.","title":"Mutual graph learning for camouflaged object detection","authors":"Zhai, F Li, C Yang, H Chen, Cheng, Fan","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhang et al., 2017] P Zhang, D Wang, H Lu, H Wang, and X Ruan. Amulet: Aggregating multi-level convolutional features for salient object detection. In ICCV, 2017.","title":"Amulet: Aggregating multi-level convolutional features for salient object detection","authors":"D Zhang, H Wang, H Lu, Wang, Ruan","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Zhang et al., 2020] J Zhang, D-P Fan, Y Dai, S Anwar, F S Saleh, T Zhang, and N Barnes. Uc-net: Uncertainty in- spired rgb-d saliency detection via conditional variational autoencoders. In CVPR, 2020.","title":"Uc-net: Uncertainty inspired rgb-d saliency detection via conditional variational autoencoders","authors":"D-P Zhang, Y Fan, S Dai, F S Anwar, T Saleh, Zhang, Barnes","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Zhao et al., 2019] J-X Zhao, J-J Liu, D-P Fan, Y Cao, J Yang, and M-M Cheng. Egnet: Edge guidance network for salient object detection. In CVPR, 2019.","title":"Egnet: Edge guidance network for salient object detection","authors":"J-X Zhao, J-J Liu, D-P Fan, Y Cao, J Yang, M-M Cheng","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Zhou et al., 2020] H Zhou, X Xie, J Lai, Z Chen, and L Yang. Interactive two-stream decoder for accurate and fast saliency detection. In CVPR, 2020.","title":"Interactive two-stream decoder for accurate and fast saliency detection","authors":"X Zhou, J Xie, Z Lai, L Chen, Yang","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}