{"type":"ScholarlyArticle","title":"Context-aware Cross-level Fusion Network for Camouflaged Object Detection","authors":[{"name":"Yujia Sun","slug":"yujia-sun","given":"Yujia","family":"Sun","affiliation":""},{"name":"Geng Chen","slug":"geng-chen","given":"Geng","family":"Chen","affiliation":""},{"name":"Tao Zhou","slug":"tao-zhou","given":"Tao","family":"Zhou","affiliation":""},{"name":"Yi Zhang","slug":"yi-zhang","given":"Yi","family":"Zhang","affiliation":""},{"name":"Nian Liu","slug":"nian-liu","given":"Nian","family":"Liu","affiliation":""}],"abstract":"Camouflaged object detection (COD) is a challenging task due to the low boundary contrast between the object and its surroundings. In addition, the appearance of camouflaged objects varies significantly, e.g., object size and shape, aggravating the difficulties of accurate COD. In this paper, we propose a novel Context-aware Cross\u0002level Fusion Network (C2F-Net) to address the challenging COD task. Specifically, we propose an Attention-induced Cross-level Fusion Module (ACFM) to integrate the multi-level features with\r\ninformative attention coefficients. The fused features are then fed to the proposed Dual-branch Global Context Module (DGCM), which yields multi-scale feature representations for exploiting rich global context information. In C2F-Net, the two modules are conducted on high-level features using a cascaded manner. Extensive experiments on three widely used benchmark datasets demonstrate that our C2F-Net is an effective COD model and outperforms state-of-the-art models remarkably. Our code is publicly available at:\r\nhttps://github.com/thograce/C2FNet.","doi":"10.24963/ijcai.2021/142","url":"https://ijcai.org/proceedings/2021/142","pdf":"https://ijcai.org/proceedings/2021/0142.pdf","markdown":"https://ijcai.org/proceedings/2021/142.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/142","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Computer Vision II","track":"Main Track","number":142,"pages":{"first":1025,"last":1031},"keywords":["Computer Vision: 2D and 3D Computer Vision"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}