{"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/cross-modality-knowledge-distillation-network","title":"Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection","arxiv_id":"2211.07171","date":"2022-11-14","proceeding":null,"authors":["Yu Hong","Hang Dai","Yong Ding"],"abstract":"Leveraging LiDAR-based detectors or real LiDAR point data to guide monocular 3D detection has brought significant improvement, e.g., Pseudo-LiDAR methods. However, the existing methods usually apply non-end-to-end training strategies and insufficiently leverage the LiDAR information, where the rich potential of the LiDAR data has not been well exploited. In this paper, we propose the Cross-Modality Knowledge Distillation (CMKD) network for monocular 3D detection to efficiently and directly transfer the knowledge from LiDAR modality to image modality on both features and responses. Moreover, we further extend CMKD as a semi-supervised training framework by distilling knowledge from large-scale unlabeled data and significantly boost the performance. Until submission, CMKD ranks $1^{st}$ among the monocular 3D detectors with publications on both KITTI $test$ set and Waymo $val$ set with significant performance gains compared to previous state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2211.07171v1","url_pdf":"https://arxiv.org/pdf/2211.07171v1.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":"cross-modality-knowledge-distillation-network","repo_url":"https://github.com/Cc-Hy/CMKD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"monocular-3d-object-detection","task_name":"Monocular 3D Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-3d-object-detection-on-kitti-cars-2","task":"Monocular 3D Object Detection","dataset":"KITTI Cars Easy","model":"CMKD","rank_in_archive_order":2,"of":5,"metrics":{"AP Easy":"28.55"},"uses_additional_data":true},{"leaderboard":"/sota/monocular-3d-object-detection-on-kitti-cars-1","task":"Monocular 3D Object Detection","dataset":"KITTI Cars Hard","model":"CMKD","rank_in_archive_order":2,"of":7,"metrics":{"AP Hard":"16.77"},"uses_additional_data":true},{"leaderboard":"/sota/monocular-3d-object-detection-on-kitti-5","task":"Monocular 3D Object Detection","dataset":"KITTI Cyclist Easy","model":"CMKD","rank_in_archive_order":1,"of":2,"metrics":{"AP Easy":"12.52"},"uses_additional_data":true},{"leaderboard":"/sota/monocular-3d-object-detection-on-kitti-7","task":"Monocular 3D Object Detection","dataset":"KITTI Cyclist Hard","model":"CMKD","rank_in_archive_order":1,"of":2,"metrics":{"AP Hard":"6.34"},"uses_additional_data":true},{"leaderboard":"/sota/monocular-3d-object-detection-on-kitti-6","task":"Monocular 3D Object Detection","dataset":"KITTI Cyclist Moderate","model":"CMKD","rank_in_archive_order":1,"of":2,"metrics":{"AP Medium":"6.67"},"uses_additional_data":true},{"leaderboard":"/sota/monocular-3d-object-detection-on-kitti-3","task":"Monocular 3D Object Detection","dataset":"KITTI Pedestrian Easy","model":"CMKD","rank_in_archive_order":1,"of":3,"metrics":{"AP Easy":"13.94"},"uses_additional_data":true},{"leaderboard":"/sota/monocular-3d-object-detection-on-kitti-1","task":"Monocular 3D Object Detection","dataset":"KITTI Pedestrian Hard","model":"CMKD","rank_in_archive_order":2,"of":4,"metrics":{"AP Hard":"7.42"},"uses_additional_data":true},{"leaderboard":"/sota/monocular-3d-object-detection-on-kitti-4","task":"Monocular 3D Object Detection","dataset":"KITTI Pedestrian Moderate","model":"CMKD","rank_in_archive_order":2,"of":3,"metrics":{"AP Medium":"8.79"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.07171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.07171"}},"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/Cc-Hy/CMKD","reach":null}],"summary":{"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":"5c82daed4533966c","entry":"Detector3DTemplate_CMKD","repo":"Cc-Hy/CMKD","repo_kind":"official","path":"pcdet/models/detectors/cmkd.py","file_url":"https://github.com/Cc-Hy/CMKD/blob/HEAD/pcdet/models/detectors/cmkd.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":"5c82daed4533966c"}},{"code_sha256_prefix":"7767c10537520cad","entry":"CMKD_MONO","repo":"Cc-Hy/CMKD","repo_kind":"official","path":"pcdet/models/detectors/cmkd.py","file_url":"https://github.com/Cc-Hy/CMKD/blob/HEAD/pcdet/models/detectors/cmkd.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":"7767c10537520cad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}