{"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/unidistill-a-universal-cross-modality","title":"UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View","arxiv_id":"2303.15083","date":"2023-03-27","proceeding":"CVPR 2023 1","authors":["Shengchao Zhou","Weizhou Liu","Chen Hu","Shuchang Zhou","Chao Ma"],"abstract":"In the field of 3D object detection for autonomous driving, the sensor portfolio including multi-modality and single-modality is diverse and complex. Since the multi-modal methods have system complexity while the accuracy of single-modal ones is relatively low, how to make a tradeoff between them is difficult. In this work, we propose a universal cross-modality knowledge distillation framework (UniDistill) to improve the performance of single-modality detectors. Specifically, during training, UniDistill projects the features of both the teacher and the student detector into Bird's-Eye-View (BEV), which is a friendly representation for different modalities. Then, three distillation losses are calculated to sparsely align the foreground features, helping the student learn from the teacher without introducing additional cost during inference. Taking advantage of the similar detection paradigm of different detectors in BEV, UniDistill easily supports LiDAR-to-camera, camera-to-LiDAR, fusion-to-LiDAR and fusion-to-camera distillation paths. Furthermore, the three distillation losses can filter the effect of misaligned background information and balance between objects of different sizes, improving the distillation effectiveness. Extensive experiments on nuScenes demonstrate that UniDistill effectively improves the mAP and NDS of student detectors by 2.0%~3.2%.","url_abs":"https://arxiv.org/abs/2303.15083v1","url_pdf":"https://arxiv.org/pdf/2303.15083v1.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":"unidistill-a-universal-cross-modality","repo_url":"https://github.com/megvii-research/cvpr2023-unidistill","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":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.15083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15083"}},"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/megvii-research/cvpr2023-unidistill","reach":null}],"summary":{"ran_fixture":1,"ran_honours":2},"by_repo_kind":{"official":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"6146369bb4aae695","entry":"FeatureDistillLoss","repo":"megvii-research/cvpr2023-unidistill","repo_kind":"official","path":"unidistill/exps/multisensor_fusion/nuscenes/BEVFusion/BEVFusion_nuscenes_centerhead_camera_exp_distill_fusion.py","file_url":"https://github.com/megvii-research/cvpr2023-unidistill/blob/HEAD/unidistill/exps/multisensor_fusion/nuscenes/BEVFusion/BEVFusion_nuscenes_centerhead_camera_exp_distill_fusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6146369bb4aae695"}},{"code_sha256_prefix":"11790e16efd1a8d4","entry":"reduce_mean","repo":"megvii-research/cvpr2023-unidistill","repo_kind":"official","path":"unidistill/exps/multisensor_fusion/nuscenes/BEVFusion/BEVFusion_nuscenes_centerhead_camera_exp_distill_fusion.py","file_url":"https://github.com/megvii-research/cvpr2023-unidistill/blob/HEAD/unidistill/exps/multisensor_fusion/nuscenes/BEVFusion/BEVFusion_nuscenes_centerhead_camera_exp_distill_fusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"11790e16efd1a8d4"}},{"code_sha256_prefix":"350276fe38eb1d9f","entry":"reduce_sum","repo":"megvii-research/cvpr2023-unidistill","repo_kind":"official","path":"unidistill/exps/multisensor_fusion/nuscenes/BEVFusion/BEVFusion_nuscenes_centerhead_camera_exp_distill_fusion.py","file_url":"https://github.com/megvii-research/cvpr2023-unidistill/blob/HEAD/unidistill/exps/multisensor_fusion/nuscenes/BEVFusion/BEVFusion_nuscenes_centerhead_camera_exp_distill_fusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"350276fe38eb1d9f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}