{"url":"/method/basnet","slug":"basnet","name":"BASNet","full_name":"Boundary-Aware Segmentation Network","full_name_withheld":false,"description_markdown":"**BASNet**, or **Boundary-Aware Segmentation Network**, is an image segmentation architecture that consists of a predict-refine architecture and a hybrid loss. The proposed BASNet comprises a predict-refine architecture and a hybrid loss, for highly accurate image segmentation.  The predict-refine architecture consists of a densely supervised encoder-decoder network and a residual \r\n refinement module, which are respectively used to predict and refine a segmentation probability map. The hybrid loss is a combination of the binary cross entropy, structural similarity and intersection-over-union losses, which guide the network to learn three-level (i.e., pixel-, patch- and map- level) hierarchy representations.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Boundary-Aware Segmentation Network for Mobile and Web Applications","paper":"/paper/boundary-aware-segmentation-network-for","first_author":"Xuebin Qin","n_authors":9,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/boundary-aware-segmentation-network-for"},"source":{"url":"https://arxiv.org/abs/2101.04704v2","title":"Boundary-Aware Segmentation Network for Mobile and Web Applications","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Semantic Segmentation Models","url":"/methods/category/semantic-segmentation-models","pwc_aliases":["segmentation-models"]}],"n_papers_tagged":4,"archive_num_papers":4,"papers_newest_first":[{"paper":"/paper/udbrnet-a-novel-uncertainty-driven-boundary","title":"UDBRNet: A novel uncertainty driven boundary refined network for organ at risk segmentation","date":"2024-06-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection","date":"2021-09-04","arxiv_id":"2109.01770","n_code_links":0,"syntology":null},{"paper":null,"title":"Weakly-Supervised Temporal Action Localization Through Local-Global Background Modeling","date":"2021-06-20","arxiv_id":"2106.11811","n_code_links":0,"syntology":null},{"paper":"/paper/boundary-aware-segmentation-network-for","title":"Boundary-Aware Segmentation Network for Mobile and Web Applications","date":"2021-01-12","arxiv_id":"2101.04704","n_code_links":5,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":1}}],"papers_shown":4,"tasks":[{"task":"/task/segmentation","name":"Segmentation","papers":2},{"task":"/task/weakly-supervised-learning","name":"Weakly-supervised Learning","papers":2},{"task":"/task/action-localization","name":"Action Localization","papers":1},{"task":"/task/camouflaged-object-segmentation","name":"Camouflaged Object Segmentation","papers":1},{"task":"/task/decoder","name":"Decoder","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":1},{"task":"/task/object","name":"Object","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/organ-segmentation","name":"Organ Segmentation","papers":1},{"task":"/task/salient-object-detection-1","name":"Salient Object Detection","papers":1},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":1},{"task":"/task/action-recognition","name":"Temporal Action Localization","papers":1},{"task":"/task/weakly-supervised-temporal-action","name":"Weakly-supervised Temporal Action Localization","papers":1},{"task":"/task/object-detection-1","name":"object-detection","papers":1}],"tasks_shown":15,"n_tasks":15,"usage_by_year":[{"year":"2021","papers":3},{"year":"2024","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/basnet"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}