{"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/towards-efficient-3d-object-detection-with","title":"Towards Efficient 3D Object Detection with Knowledge Distillation","arxiv_id":"2205.15156","date":"2022-05-30","proceeding":null,"authors":["Jihan Yang","Shaoshuai Shi","Runyu Ding","Zhe Wang","Xiaojuan Qi"],"abstract":"Despite substantial progress in 3D object detection, advanced 3D detectors often suffer from heavy computation overheads. To this end, we explore the potential of knowledge distillation (KD) for developing efficient 3D object detectors, focusing on popular pillar- and voxel-based detectors.In the absence of well-developed teacher-student pairs, we first study how to obtain student models with good trade offs between accuracy and efficiency from the perspectives of model compression and input resolution reduction. Then, we build a benchmark to assess existing KD methods developed in the 2D domain for 3D object detection upon six well-constructed teacher-student pairs. Further, we propose an improved KD pipeline incorporating an enhanced logit KD method that performs KD on only a few pivotal positions determined by teacher classification response, and a teacher-guided student model initialization to facilitate transferring teacher model's feature extraction ability to students through weight inheritance. Finally, we conduct extensive experiments on the Waymo dataset. Our best performing model achieves $65.75\\%$ LEVEL 2 mAPH, surpassing its teacher model and requiring only $44\\%$ of teacher flops. Our most efficient model runs 51 FPS on an NVIDIA A100, which is $2.2\\times$ faster than PointPillar with even higher accuracy. Code is available at \\url{https://github.com/CVMI-Lab/SparseKD}.","url_abs":"https://arxiv.org/abs/2205.15156v3","url_pdf":"https://arxiv.org/pdf/2205.15156v3.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":"towards-efficient-3d-object-detection-with","repo_url":"https://github.com/cvmi-lab/sparsekd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"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":"model-compression","task_name":"Model Compression"},{"task_slug":"object","task_name":"Object"},{"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":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.15156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.15156"}},"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/cvmi-lab/sparsekd","reach":null}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"3435b15402d06550","entry":"AnchorLogitKDHead","repo":"cvmi-lab/sparsekd","repo_kind":"official","path":"pcdet/models/kd_heads/anchor_head/anchor_logit_kd_head.py","file_url":"https://github.com/cvmi-lab/sparsekd/blob/HEAD/pcdet/models/kd_heads/anchor_head/anchor_logit_kd_head.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":"3435b15402d06550"}},{"code_sha256_prefix":"6785eadf09178b3e","entry":"KDHeadTemplate","repo":"cvmi-lab/sparsekd","repo_kind":"official","path":"pcdet/models/kd_heads/anchor_head/anchor_logit_kd_head.py","file_url":"https://github.com/cvmi-lab/sparsekd/blob/HEAD/pcdet/models/kd_heads/anchor_head/anchor_logit_kd_head.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":"6785eadf09178b3e"}},{"code_sha256_prefix":"5c47c98e788ba6cb","entry":"boxes_iou3d_gpu","repo":"cvmi-lab/sparsekd","repo_kind":"official","path":"pcdet/models/kd_heads/anchor_head/anchor_logit_kd_head.py","file_url":"https://github.com/cvmi-lab/sparsekd/blob/HEAD/pcdet/models/kd_heads/anchor_head/anchor_logit_kd_head.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":"5c47c98e788ba6cb"}},{"code_sha256_prefix":"799d392cab9c82f8","entry":"points_in_boxes_gpu","repo":"cvmi-lab/sparsekd","repo_kind":"official","path":"pcdet/models/kd_heads/anchor_head/anchor_logit_kd_head.py","file_url":"https://github.com/cvmi-lab/sparsekd/blob/HEAD/pcdet/models/kd_heads/anchor_head/anchor_logit_kd_head.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":"799d392cab9c82f8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}