{"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/train-in-germany-test-in-the-usa-making-3d","title":"Train in Germany, Test in The USA: Making 3D Object Detectors Generalize","arxiv_id":"2005.08139","date":"2020-05-17","proceeding":"CVPR 2020 6","authors":["Yan Wang","Xiangyu Chen","Yurong You","Li Erran","Bharath Hariharan","Mark Campbell","Kilian Q. Weinberger","Wei-Lun Chao"],"abstract":"In the domain of autonomous driving, deep learning has substantially improved the 3D object detection accuracy for LiDAR and stereo camera data alike. While deep networks are great at generalization, they are also notorious to over-fit to all kinds of spurious artifacts, such as brightness, car sizes and models, that may appear consistently throughout the data. In fact, most datasets for autonomous driving are collected within a narrow subset of cities within one country, typically under similar weather conditions. In this paper we consider the task of adapting 3D object detectors from one dataset to another. We observe that naively, this appears to be a very challenging task, resulting in drastic drops in accuracy levels. We provide extensive experiments to investigate the true adaptation challenges and arrive at a surprising conclusion: the primary adaptation hurdle to overcome are differences in car sizes across geographic areas. A simple correction based on the average car size yields a strong correction of the adaptation gap. Our proposed method is simple and easily incorporated into most 3D object detection frameworks. It provides a first baseline for 3D object detection adaptation across countries, and gives hope that the underlying problem may be more within grasp than one may have hoped to believe. Our code is available at https://github.com/cxy1997/3D_adapt_auto_driving.","url_abs":"https://arxiv.org/abs/2005.08139v1","url_pdf":"https://arxiv.org/pdf/2005.08139v1.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":"train-in-germany-test-in-the-usa-making-3d","repo_url":"https://github.com/cxy1997/3D_adapt_auto_driving","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":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2005.08139","atlas_url":"https://app.syntology.ai/?focus=2005.08139","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08139"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/cxy1997/3D_adapt_auto_driving","reach":null}],"summary":{"ran_fixture":2,"ran_draft_wrong":4,"ran_honours":1},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":7,"samples":[{"code_sha256_prefix":"338d8e3b6b1ef261","entry":"anno_to_ground","repo":"cxy1997/3D_adapt_auto_driving","repo_kind":"official","path":"evaluate/evaluate.py","file_url":"https://github.com/cxy1997/3D_adapt_auto_driving/blob/HEAD/evaluate/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"338d8e3b6b1ef261"}},{"code_sha256_prefix":"bae007593bd3dfd1","entry":"create_logger","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"bae007593bd3dfd1"}},{"code_sha256_prefix":"2f84320f2c4da396","entry":"grouper","repo":"cxy1997/3D_adapt_auto_driving","repo_kind":"official","path":"stat_norm/norm.py","file_url":"https://github.com/cxy1997/3D_adapt_auto_driving/blob/HEAD/stat_norm/norm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2f84320f2c4da396"}},{"code_sha256_prefix":"a86d4564ef1cb3c9","entry":"load_json","repo":"cxy1997/3D_adapt_auto_driving","repo_kind":"official","path":"stat_norm/norm.py","file_url":"https://github.com/cxy1997/3D_adapt_auto_driving/blob/HEAD/stat_norm/norm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a86d4564ef1cb3c9"}},{"code_sha256_prefix":"518d342a20ed61a5","entry":"read_plane","repo":"cxy1997/3D_adapt_auto_driving","repo_kind":"official","path":"evaluate/evaluate.py","file_url":"https://github.com/cxy1997/3D_adapt_auto_driving/blob/HEAD/evaluate/evaluate.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":"518d342a20ed61a5"}},{"code_sha256_prefix":"2deeed9007bbcceb","entry":"read_planes","repo":"cxy1997/3D_adapt_auto_driving","repo_kind":"official","path":"evaluate/evaluate.py","file_url":"https://github.com/cxy1997/3D_adapt_auto_driving/blob/HEAD/evaluate/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2deeed9007bbcceb"}},{"code_sha256_prefix":"d7be200a5f526a1c","entry":"single_scale","repo":"cxy1997/3D_adapt_auto_driving","repo_kind":"official","path":"stat_norm/norm.py","file_url":"https://github.com/cxy1997/3D_adapt_auto_driving/blob/HEAD/stat_norm/norm.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d7be200a5f526a1c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}