{"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/pyramid-grafting-network-for-one-stage-high","title":"Pyramid Grafting Network for One-Stage High Resolution Saliency Detection","arxiv_id":"2204.05041","date":"2022-04-11","proceeding":"CVPR 2022 1","authors":["Chenxi Xie","Changqun Xia","Mingcan Ma","Zhirui Zhao","Xiaowu Chen","Jia Li"],"abstract":"Recent salient object detection (SOD) methods based on deep neural network have achieved remarkable performance. However, most of existing SOD models designed for low-resolution input perform poorly on high-resolution images due to the contradiction between the sampling depth and the receptive field size. Aiming at resolving this contradiction, we propose a novel one-stage framework called Pyramid Grafting Network (PGNet), using transformer and CNN backbone to extract features from different resolution images independently and then graft the features from transformer branch to CNN branch. An attention-based Cross-Model Grafting Module (CMGM) is proposed to enable CNN branch to combine broken detailed information more holistically, guided by different source feature during decoding process. Moreover, we design an Attention Guided Loss (AGL) to explicitly supervise the attention matrix generated by CMGM to help the network better interact with the attention from different models. We contribute a new Ultra-High-Resolution Saliency Detection dataset UHRSD, containing 5,920 images at 4K-8K resolutions. To our knowledge, it is the largest dataset in both quantity and resolution for high-resolution SOD task, which can be used for training and testing in future research. Sufficient experiments on UHRSD and widely-used SOD datasets demonstrate that our method achieves superior performance compared to the state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2204.05041v2","url_pdf":"https://arxiv.org/pdf/2204.05041v2.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":"pyramid-grafting-network-for-one-stage-high","repo_url":"https://github.com/icvteam/pgnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"4k","task_name":"4k"},{"task_slug":null,"task_name":"8k"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"salient-object-detection","task_name":"RGB Salient Object Detection"},{"task_slug":"saliency-detection","task_name":"Saliency Detection"},{"task_slug":"salient-object-detection-1","task_name":"Salient Object Detection"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"low-resolution-input","method_name":"Low-resolution input"}],"datasets_introduced":[{"slug":"uhrsd","name":"UHRSD","full_name":"Ultra High-Resolution Saliency Detection Dataset"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/rgb-salient-object-detection-on-davis-s","task":"RGB Salient Object Detection","dataset":"DAVIS-S","model":"PGNet (HRSOD, UHRSD)","rank_in_archive_order":8,"of":12,"metrics":{"F-measure":"0.956","MAE":"0.010","S-measure":"0.954","mBA":"0.730"},"uses_additional_data":true},{"leaderboard":"/sota/rgb-salient-object-detection-on-davis-s","task":"RGB Salient Object Detection","dataset":"DAVIS-S","model":"PGNet (DUTS, HRSOD)","rank_in_archive_order":9,"of":12,"metrics":{"F-measure":"0.948","MAE":"0.012","S-measure":"0.947","mBA":"0.716"},"uses_additional_data":true},{"leaderboard":"/sota/rgb-salient-object-detection-on-davis-s","task":"RGB Salient Object Detection","dataset":"DAVIS-S","model":"PGNet","rank_in_archive_order":10,"of":12,"metrics":{"F-measure":"0.931","MAE":"0.015","S-measure":"0.935","mBA":"0.707"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-salient-object-detection-on-hrsod","task":"RGB Salient Object Detection","dataset":"HRSOD","model":"PGNet (HRSOD, UHRSD)","rank_in_archive_order":10,"of":14,"metrics":{"MAE":"0.020","S-Measure":"0.938","mBA":"0.727","max F-Measure":"0.939"},"uses_additional_data":true},{"leaderboard":"/sota/rgb-salient-object-detection-on-hrsod","task":"RGB Salient Object Detection","dataset":"HRSOD","model":"PGNet (DUTS, HRSOD)","rank_in_archive_order":11,"of":14,"metrics":{"MAE":"0.020","S-Measure":"0.935","mBA":"0.714","max F-Measure":"0.929"},"uses_additional_data":true},{"leaderboard":"/sota/rgb-salient-object-detection-on-hrsod","task":"RGB Salient Object Detection","dataset":"HRSOD","model":"PGNet","rank_in_archive_order":12,"of":14,"metrics":{"MAE":"0.021","S-Measure":"0.930","mBA":"0.693","max F-Measure":"0.922"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-salient-object-detection-on-uhrsd","task":"RGB Salient Object Detection","dataset":"UHRSD","model":"PGNet (HRSOD, UHRSD)","rank_in_archive_order":8,"of":12,"metrics":{"MAE":"0.026","S-Measure":"0.935","mBA":"0.765","max F-Measure":"0.930"},"uses_additional_data":true},{"leaderboard":"/sota/rgb-salient-object-detection-on-uhrsd","task":"RGB Salient Object Detection","dataset":"UHRSD","model":"PGNet (DUTS, HRSOD)","rank_in_archive_order":11,"of":12,"metrics":{"MAE":"0.036","S-Measure":"0.912","mBA":"0.735","max F-Measure":"0.915"},"uses_additional_data":true},{"leaderboard":"/sota/rgb-salient-object-detection-on-uhrsd","task":"RGB Salient Object Detection","dataset":"UHRSD","model":"PGNet","rank_in_archive_order":12,"of":12,"metrics":{"MAE":"0.037","S-Measure":"0.912","mBA":"0.715","max F-Measure":"0.914"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2204.05041","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.05041"}},"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/icvteam/pgnet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":3,"unverified":4},"by_repo_kind":{"official":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"144d10b49baeb8a6","entry":"window_partition","repo":"icvteam/pgnet","repo_kind":"official","path":"src/Swin.py","file_url":"https://github.com/icvteam/pgnet/blob/HEAD/src/Swin.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":"icvteam/pgnet","repo_kind":"official","path":"src/Res.py","file_url":"https://github.com/icvteam/pgnet/blob/HEAD/src/Res.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"icvteam/pgnet","repo_kind":"official","path":"src/Res.py","file_url":"https://github.com/icvteam/pgnet/blob/HEAD/src/Res.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"160bb14bd76201b4"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","repo":"icvteam/pgnet","repo_kind":"official","path":"src/Swin.py","file_url":"https://github.com/icvteam/pgnet/blob/HEAD/src/Swin.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"61bf152e6a42a184"}},{"code_sha256_prefix":"511bb698068a5ab2","entry":"att_loss","repo":"icvteam/pgnet","repo_kind":"official","path":"src/train_distributed.py","file_url":"https://github.com/icvteam/pgnet/blob/HEAD/src/train_distributed.py","link_basis":"harvester_set","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":"511bb698068a5ab2"}},{"code_sha256_prefix":"c38a7654a6ffd39c","entry":"bce_iou_loss","repo":"icvteam/pgnet","repo_kind":"official","path":"src/train_distributed.py","file_url":"https://github.com/icvteam/pgnet/blob/HEAD/src/train_distributed.py","link_basis":"harvester_set","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":"c38a7654a6ffd39c"}},{"code_sha256_prefix":"3fd7d0fe23fd7f1d","entry":"flat","repo":"icvteam/pgnet","repo_kind":"official","path":"src/train_distributed.py","file_url":"https://github.com/icvteam/pgnet/blob/HEAD/src/train_distributed.py","link_basis":"harvester_set","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":"3fd7d0fe23fd7f1d"}},{"code_sha256_prefix":"5f8138790ab61efe","entry":"resnet18","repo":"icvteam/pgnet","repo_kind":"official","path":"src/Res.py","file_url":"https://github.com/icvteam/pgnet/blob/HEAD/src/Res.py","link_basis":"harvester_set","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":"5f8138790ab61efe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}