{"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/salience-detr-enhancing-detection-transformer-1","title":"Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement","arxiv_id":"2403.16131","date":"2024-03-24","proceeding":"CVPR 2024 1","authors":["Xiuquan Hou","Meiqin Liu","Senlin Zhang","Ping Wei","Badong Chen"],"abstract":"DETR-like methods have significantly increased detection performance in an end-to-end manner. The mainstream two-stage frameworks of them perform dense self-attention and select a fraction of queries for sparse cross-attention, which is proven effective for improving performance but also introduces a heavy computational burden and high dependence on stable query selection. This paper demonstrates that suboptimal two-stage selection strategies result in scale bias and redundancy due to the mismatch between selected queries and objects in two-stage initialization. To address these issues, we propose hierarchical salience filtering refinement, which performs transformer encoding only on filtered discriminative queries, for a better trade-off between computational efficiency and precision. The filtering process overcomes scale bias through a novel scale-independent salience supervision. To compensate for the semantic misalignment among queries, we introduce elaborate query refinement modules for stable two-stage initialization. Based on above improvements, the proposed Salience DETR achieves significant improvements of +4.0% AP, +0.2% AP, +4.4% AP on three challenging task-specific detection datasets, as well as 49.2% AP on COCO 2017 with less FLOPs. The code is available at https://github.com/xiuqhou/Salience-DETR.","url_abs":"https://arxiv.org/abs/2403.16131v1","url_pdf":"https://arxiv.org/pdf/2403.16131v1.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":"salience-detr-enhancing-detection-transformer-1","repo_url":"https://github.com/xiuqhou/Salience-DETR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"salience-detr-enhancing-detection-transformer-1","repo_url":"https://github.com/xiuqhou/relation-detr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"salience-detr-enhancing-detection-transformer-1","repo_url":"https://github.com/xunull/read-Salience-DETR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"2d-object-detection","task_name":"2D Object Detection"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"dense-object-detection","task_name":"Dense Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"detr","method_name":"Detr"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-coco-2017-val","task":"Object Detection","dataset":"COCO 2017 val","model":"Salience-DETR (Focal-L 1x)","rank_in_archive_order":6,"of":33,"metrics":{"AP":"57.3","AP50":"75.5","AP75":"62.3","APL":"74.5","APM":"61.8","APS":"40.9","Param.":"220M"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-2017-val","task":"Object Detection","dataset":"COCO 2017 val","model":"Salience-DETR (Swin-L 1x)","rank_in_archive_order":8,"of":33,"metrics":{"AP":"56.5","AP50":"75.0","AP75":"61.5","APL":"72.8","APM":"61.2","APS":"40.2","Param.":"210M"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-2017-val","task":"Object Detection","dataset":"COCO 2017 val","model":"Salience-DETR (ResNet50 1x)","rank_in_archive_order":16,"of":33,"metrics":{"AP":"50.0","AP50":"67.7","AP75":"54.2","APL":"64.4","APM":"54.4","APS":"33.3","Param.":"56M"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.16131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16131"}},"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/xiuqhou/Salience-DETR","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xunull/read-Salience-DETR","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiuqhou/relation-detr","reach":null}],"summary":{"ran":6,"ran_draft_wrong":3,"ran_honours":2,"unverified":12},"by_repo_kind":{"official":{"samples":13,"ran":6,"repositories":1},"listed":{"samples":10,"ran":5,"repositories":2}},"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":"e54def49272a77fb","entry":"DETRBaseTransformer","repo":"xiuqhou/relation-detr","repo_kind":"listed","path":"models/bricks/relation_transformer.py","file_url":"https://github.com/xiuqhou/relation-detr/blob/HEAD/models/bricks/relation_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e54def49272a77fb"}},{"code_sha256_prefix":"88c02c4fc776a779","entry":"EvalResize","repo":"xiuqhou/Salience-DETR","repo_kind":"official","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xiuqhou/Salience-DETR/blob/HEAD/models/detectors/salience_detr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"88c02c4fc776a779"}},{"code_sha256_prefix":"5d857e337ecf6a8a","entry":"GenerateDNQueries","repo":"xiuqhou/Salience-DETR","repo_kind":"official","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xiuqhou/Salience-DETR/blob/HEAD/models/detectors/salience_detr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5d857e337ecf6a8a"}},{"code_sha256_prefix":"26df4273ae94b72a","entry":"MLP","repo":"xiuqhou/relation-detr","repo_kind":"listed","path":"models/bricks/relation_transformer.py","file_url":"https://github.com/xiuqhou/relation-detr/blob/HEAD/models/bricks/relation_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"26df4273ae94b72a"}},{"code_sha256_prefix":"f4b996d811277585","entry":"MultiLevelTransformer","repo":"xiuqhou/relation-detr","repo_kind":"listed","path":"models/bricks/relation_transformer.py","file_url":"https://github.com/xiuqhou/relation-detr/blob/HEAD/models/bricks/relation_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f4b996d811277585"}},{"code_sha256_prefix":"8d39466be24010f8","entry":"TwostageTransformer","repo":"xiuqhou/relation-detr","repo_kind":"listed","path":"models/bricks/relation_transformer.py","file_url":"https://github.com/xiuqhou/relation-detr/blob/HEAD/models/bricks/relation_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8d39466be24010f8"}},{"code_sha256_prefix":"0b3cdeb3b0b05c06","entry":"decode_labels","repo":"xiuqhou/Salience-DETR","repo_kind":"official","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xiuqhou/Salience-DETR/blob/HEAD/models/detectors/salience_detr.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0b3cdeb3b0b05c06"}},{"code_sha256_prefix":"d088164a46bf049d","entry":"encode_labels","repo":"xiuqhou/Salience-DETR","repo_kind":"official","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xiuqhou/Salience-DETR/blob/HEAD/models/detectors/salience_detr.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d088164a46bf049d"}},{"code_sha256_prefix":"4350a1d28ee65b0a","entry":"encode_labels","repo":"xunull/read-Salience-DETR","repo_kind":"listed","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xunull/read-Salience-DETR/blob/HEAD/models/detectors/salience_detr.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4350a1d28ee65b0a"}},{"code_sha256_prefix":"d4dcad186c11cc6e","entry":"image_list_from_tensors","repo":"xiuqhou/Salience-DETR","repo_kind":"official","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xiuqhou/Salience-DETR/blob/HEAD/models/detectors/salience_detr.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d4dcad186c11cc6e"}},{"code_sha256_prefix":"24d843af1035723e","entry":"inverse_sigmoid","repo":"xiuqhou/Salience-DETR","repo_kind":"official","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xiuqhou/Salience-DETR/blob/HEAD/models/detectors/salience_detr.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"24d843af1035723e"}},{"code_sha256_prefix":"b6ec17c5de8153f5","entry":"BaseDetector","repo":"xiuqhou/Salience-DETR","repo_kind":"official","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xiuqhou/Salience-DETR/blob/HEAD/models/detectors/salience_detr.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":true,"mcp_get_code":{"code_sha256":"b6ec17c5de8153f5"}},{"code_sha256_prefix":"b9d6e114bdfb48b5","entry":"BaseDetector","repo":"xunull/read-Salience-DETR","repo_kind":"listed","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xunull/read-Salience-DETR/blob/HEAD/models/detectors/salience_detr.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":true,"mcp_get_code":{"code_sha256":"b9d6e114bdfb48b5"}},{"code_sha256_prefix":"8d8d14c400dc9048","entry":"DETRDetector","repo":"xiuqhou/Salience-DETR","repo_kind":"official","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xiuqhou/Salience-DETR/blob/HEAD/models/detectors/salience_detr.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":true,"mcp_get_code":{"code_sha256":"8d8d14c400dc9048"}},{"code_sha256_prefix":"b452573f88203f9d","entry":"DETRDetector","repo":"xunull/read-Salience-DETR","repo_kind":"listed","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xunull/read-Salience-DETR/blob/HEAD/models/detectors/salience_detr.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":true,"mcp_get_code":{"code_sha256":"b452573f88203f9d"}},{"code_sha256_prefix":"e08e50fcf0e7c2e7","entry":"DNDETRDetector","repo":"xiuqhou/Salience-DETR","repo_kind":"official","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xiuqhou/Salience-DETR/blob/HEAD/models/detectors/salience_detr.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":true,"mcp_get_code":{"code_sha256":"e08e50fcf0e7c2e7"}},{"code_sha256_prefix":"4b6a428989977191","entry":"DNDETRDetector","repo":"xunull/read-Salience-DETR","repo_kind":"listed","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xunull/read-Salience-DETR/blob/HEAD/models/detectors/salience_detr.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":true,"mcp_get_code":{"code_sha256":"4b6a428989977191"}},{"code_sha256_prefix":"8806364b547cbe2c","entry":"GenerateCDNQueries","repo":"xiuqhou/Salience-DETR","repo_kind":"official","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xiuqhou/Salience-DETR/blob/HEAD/models/detectors/salience_detr.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":true,"mcp_get_code":{"code_sha256":"8806364b547cbe2c"}},{"code_sha256_prefix":"3b967208a4a214e1","entry":"InterpolationMode","repo":"xiuqhou/Salience-DETR","repo_kind":"official","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xiuqhou/Salience-DETR/blob/HEAD/models/detectors/salience_detr.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":true,"mcp_get_code":{"code_sha256":"3b967208a4a214e1"}},{"code_sha256_prefix":"4b9d0e934f46f9fd","entry":"RelationTransformer","repo":"xiuqhou/relation-detr","repo_kind":"listed","path":"models/bricks/relation_transformer.py","file_url":"https://github.com/xiuqhou/relation-detr/blob/HEAD/models/bricks/relation_transformer.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":true,"mcp_get_code":{"code_sha256":"4b9d0e934f46f9fd"}},{"code_sha256_prefix":"5127f19798539444","entry":"SalienceDETR","repo":"xiuqhou/Salience-DETR","repo_kind":"official","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xiuqhou/Salience-DETR/blob/HEAD/models/detectors/salience_detr.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":true,"mcp_get_code":{"code_sha256":"5127f19798539444"}},{"code_sha256_prefix":"7325ee0427e649c0","entry":"SalienceDETR","repo":"xunull/read-Salience-DETR","repo_kind":"listed","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xunull/read-Salience-DETR/blob/HEAD/models/detectors/salience_detr.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":true,"mcp_get_code":{"code_sha256":"7325ee0427e649c0"}},{"code_sha256_prefix":"974577b98ac3356d","entry":"_onnx_batch_images","repo":"xiuqhou/Salience-DETR","repo_kind":"official","path":"models/detectors/salience_detr.py","file_url":"https://github.com/xiuqhou/Salience-DETR/blob/HEAD/models/detectors/salience_detr.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":true,"mcp_get_code":{"code_sha256":"974577b98ac3356d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}