{"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/weakly-supervised-instance-segmentation-via","title":"Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images","arxiv_id":"2104.01526","date":"2021-04-04","proceeding":"CVPR 2021 1","authors":["Xinggang Wang","Jiapei Feng","Bin Hu","Qi Ding","Longjin Ran","Xiaoxin Chen","Wenyu Liu"],"abstract":"Humans have a strong class-agnostic object segmentation ability and can outline boundaries of unknown objects precisely, which motivates us to propose a box-supervised class-agnostic object segmentation (BoxCaseg) based solution for weakly-supervised instance segmentation. The BoxCaseg model is jointly trained using box-supervised images and salient images in a multi-task learning manner. The fine-annotated salient images provide class-agnostic and precise object localization guidance for box-supervised images. The object masks predicted by a pretrained BoxCaseg model are refined via a novel merged and dropped strategy as proxy ground truth to train a Mask R-CNN for weakly-supervised instance segmentation. Only using $7991$ salient images, the weakly-supervised Mask R-CNN is on par with fully-supervised Mask R-CNN on PASCAL VOC and significantly outperforms previous state-of-the-art box-supervised instance segmentation methods on COCO. The source code, pretrained models and datasets are available at \\url{https://github.com/hustvl/BoxCaseg}.","url_abs":"https://arxiv.org/abs/2104.01526v1","url_pdf":"https://arxiv.org/pdf/2104.01526v1.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":[],"tasks":[{"task_slug":"box-supervised-instance-segmentation","task_name":"Box-supervised Instance Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"weakly-supervised-instance-segmentation","task_name":"Weakly-supervised instance 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":[{"leaderboard":"/sota/box-supervised-instance-segmentation-on-coco","task":"Box-supervised Instance Segmentation","dataset":"COCO test-dev","model":"BoxCaseg","rank_in_archive_order":5,"of":7,"metrics":{"mask AP":"30.9"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.01526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.01526"}},"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":"deterministic:regex_extraction","url":"https://github.com/hustvl/BoxCaseg","reach":null}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"found_in_text":{"samples":5,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"964a04062752cca3","entry":"BasicBlock","repo":"hustvl/BoxCaseg","repo_kind":"found_in_text","path":"joint_training/lib/models/seg_hrnet_trans_fcn.py","file_url":"https://github.com/hustvl/BoxCaseg/blob/HEAD/joint_training/lib/models/seg_hrnet_trans_fcn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"964a04062752cca3"}},{"code_sha256_prefix":"2f43e25b9234b456","entry":"Bottleneck","repo":"hustvl/BoxCaseg","repo_kind":"found_in_text","path":"joint_training/lib/models/seg_hrnet_trans_fcn.py","file_url":"https://github.com/hustvl/BoxCaseg/blob/HEAD/joint_training/lib/models/seg_hrnet_trans_fcn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f43e25b9234b456"}},{"code_sha256_prefix":"f522de39748a9384","entry":"HighResolutionModule","repo":"hustvl/BoxCaseg","repo_kind":"found_in_text","path":"joint_training/lib/models/seg_hrnet_trans_fcn.py","file_url":"https://github.com/hustvl/BoxCaseg/blob/HEAD/joint_training/lib/models/seg_hrnet_trans_fcn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f522de39748a9384"}},{"code_sha256_prefix":"7d622b71e002cae1","entry":"HighResolutionNet","repo":"hustvl/BoxCaseg","repo_kind":"found_in_text","path":"joint_training/lib/models/seg_hrnet_trans_fcn.py","file_url":"https://github.com/hustvl/BoxCaseg/blob/HEAD/joint_training/lib/models/seg_hrnet_trans_fcn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d622b71e002cae1"}},{"code_sha256_prefix":"6df419d8320dad63","entry":"Transfer","repo":"hustvl/BoxCaseg","repo_kind":"found_in_text","path":"joint_training/lib/models/seg_hrnet_trans_fcn.py","file_url":"https://github.com/hustvl/BoxCaseg/blob/HEAD/joint_training/lib/models/seg_hrnet_trans_fcn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6df419d8320dad63"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}