{"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/shelf-supervised-multi-modal-pre-training-for","title":"Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detection","arxiv_id":"2406.10115","date":"2024-06-14","proceeding":null,"authors":["Mehar Khurana","Neehar Peri","James Hays","Deva Ramanan"],"abstract":"State-of-the-art 3D object detectors are often trained on massive labeled datasets. However, annotating 3D bounding boxes remains prohibitively expensive and time-consuming, particularly for LiDAR. Instead, recent works demonstrate that self-supervised pre-training with unlabeled data can improve detection accuracy with limited labels. Contemporary methods adapt best-practices for self-supervised learning from the image domain to point clouds (such as contrastive learning). However, publicly available 3D datasets are considerably smaller and less diverse than those used for image-based self-supervised learning, limiting their effectiveness. We do note, however, that such 3D data is naturally collected in a multimodal fashion, often paired with images. Rather than pre-training with only self-supervised objectives, we argue that it is better to bootstrap point cloud representations using image-based foundation models trained on internet-scale data. Specifically, we propose a shelf-supervised approach (e.g. supervised with off-the-shelf image foundation models) for generating zero-shot 3D bounding boxes from paired RGB and LiDAR data. Pre-training 3D detectors with such pseudo-labels yields significantly better semi-supervised detection accuracy than prior self-supervised pretext tasks. Importantly, we show that image-based shelf-supervision is helpful for training LiDAR-only, RGB-only and multi-modal (RGB + LiDAR) detectors. We demonstrate the effectiveness of our approach on nuScenes and WOD, significantly improving over prior work in limited data settings. Our code is available at https://github.com/meharkhurana03/cm3d","url_abs":"https://arxiv.org/abs/2406.10115v3","url_pdf":"https://arxiv.org/pdf/2406.10115v3.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":"shelf-supervised-multi-modal-pre-training-for","repo_url":"https://github.com/meharkhurana03/cm3d","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":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.10115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10115"}},"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/meharkhurana03/cm3d","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"bafedd171a5e2fe0","entry":"category_to_detection_name_rare","repo":"meharkhurana03/cm3d","repo_kind":"official","path":"src/nuscenes/eval_custom.py","file_url":"https://github.com/meharkhurana03/cm3d/blob/HEAD/src/nuscenes/eval_custom.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bafedd171a5e2fe0"}},{"code_sha256_prefix":"01c8adafcdc868ab","entry":"count_frames","repo":"meharkhurana03/cm3d","repo_kind":"official","path":"src/kitti/2d_to_3d.py","file_url":"https://github.com/meharkhurana03/cm3d/blob/HEAD/src/kitti/2d_to_3d.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"01c8adafcdc868ab"}},{"code_sha256_prefix":"d9f5cf8b5974b645","entry":"get_medoid","repo":"meharkhurana03/cm3d","repo_kind":"official","path":"src/kitti/2d_to_3d.py","file_url":"https://github.com/meharkhurana03/cm3d/blob/HEAD/src/kitti/2d_to_3d.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d9f5cf8b5974b645"}},{"code_sha256_prefix":"21eabbf9ef6b606d","entry":"clusters_hdbscan","repo":"meharkhurana03/cm3d","repo_kind":"official","path":"src/kitti/2d_to_3d.py","file_url":"https://github.com/meharkhurana03/cm3d/blob/HEAD/src/kitti/2d_to_3d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"21eabbf9ef6b606d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}