{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/boundary-preserving-mask-r-cnn","title":"Boundary-preserving Mask R-CNN","arxiv_id":"2007.08921","date":"2020-07-17","proceeding":"ECCV 2020 8","authors":["Tianheng Cheng","Xinggang Wang","Lichao Huang","Wenyu Liu"],"abstract":"Tremendous efforts have been made to improve mask localization accuracy in instance segmentation. Modern instance segmentation methods relying on fully convolutional networks perform pixel-wise classification, which ignores object boundaries and shapes, leading coarse and indistinct mask prediction results and imprecise localization. To remedy these problems, we propose a conceptually simple yet effective Boundary-preserving Mask R-CNN (BMask R-CNN) to leverage object boundary information to improve mask localization accuracy. BMask R-CNN contains a boundary-preserving mask head in which object boundary and mask are mutually learned via feature fusion blocks. As a result, the predicted masks are better aligned with object boundaries. Without bells and whistles, BMask R-CNN outperforms Mask R-CNN by a considerable margin on the COCO dataset; in the Cityscapes dataset, there are more accurate boundary groundtruths available, so that BMask R-CNN obtains remarkable improvements over Mask R-CNN. Besides, it is not surprising to observe that BMask R-CNN obtains more obvious improvement when the evaluation criterion requires better localization (e.g., AP$_{75}$) as shown in Fig.1. Code and models are available at \\url{https://github.com/hustvl/BMaskR-CNN}.","url_abs":"https://arxiv.org/abs/2007.08921v1","url_pdf":"https://arxiv.org/pdf/2007.08921v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"boundary-preserving-mask-r-cnn","repo_url":"https://github.com/hustvl/BMaskR-CNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.08921","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.08921"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hustvl/BMaskR-CNN","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":7,"samples":[{"code_sha256_prefix":"e8526a516b4f9206","entry":"convert_basic_c2_names","repo":"hustvl/BMaskR-CNN","repo_kind":"official","path":"detectron2/checkpoint/c2_model_loading.py","file_url":"https://github.com/hustvl/BMaskR-CNN/blob/HEAD/detectron2/checkpoint/c2_model_loading.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e8526a516b4f9206"}},{"code_sha256_prefix":"52810b504f0d1066","entry":"convert_c2_detectron_names","repo":"hustvl/BMaskR-CNN","repo_kind":"official","path":"detectron2/checkpoint/c2_model_loading.py","file_url":"https://github.com/hustvl/BMaskR-CNN/blob/HEAD/detectron2/checkpoint/c2_model_loading.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"52810b504f0d1066"}},{"code_sha256_prefix":"406f84cf799ed34d","entry":"pad_masks","repo":"hustvl/BMaskR-CNN","repo_kind":"official","path":"detectron2/layers/mask_ops.py","file_url":"https://github.com/hustvl/BMaskR-CNN/blob/HEAD/detectron2/layers/mask_ops.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"406f84cf799ed34d"}},{"code_sha256_prefix":"d03592674030077f","entry":"paste_mask_in_image_old","repo":"hustvl/BMaskR-CNN","repo_kind":"official","path":"detectron2/layers/mask_ops.py","file_url":"https://github.com/hustvl/BMaskR-CNN/blob/HEAD/detectron2/layers/mask_ops.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d03592674030077f"}},{"code_sha256_prefix":"dce29c2ceb3a4117","entry":"boundary_loss_func","repo":"hustvl/BMaskR-CNN","repo_kind":"official","path":"projects/BMaskR-CNN/bmaskrcnn/mask_head.py","file_url":"https://github.com/hustvl/BMaskR-CNN/blob/HEAD/projects/BMaskR-CNN/bmaskrcnn/mask_head.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"dce29c2ceb3a4117"}},{"code_sha256_prefix":"44638936059b68e8","entry":"dice_loss_func","repo":"hustvl/BMaskR-CNN","repo_kind":"official","path":"projects/BMaskR-CNN/bmaskrcnn/mask_head.py","file_url":"https://github.com/hustvl/BMaskR-CNN/blob/HEAD/projects/BMaskR-CNN/bmaskrcnn/mask_head.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"44638936059b68e8"}},{"code_sha256_prefix":"5837267fa2aed31c","entry":"paste_masks_in_image","repo":"hustvl/BMaskR-CNN","repo_kind":"official","path":"detectron2/layers/mask_ops.py","file_url":"https://github.com/hustvl/BMaskR-CNN/blob/HEAD/detectron2/layers/mask_ops.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"5837267fa2aed31c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}