{"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/dpo-dual-perturbation-optimization-for-test","title":"DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection","arxiv_id":"2406.13891","date":"2024-06-19","proceeding":null,"authors":["Zhuoxiao Chen","Zixin Wang","Yadan Luo","Sen Wang","Zi Huang"],"abstract":"LiDAR-based 3D object detection has seen impressive advances in recent times. However, deploying trained 3D detectors in the real world often yields unsatisfactory performance when the distribution of the test data significantly deviates from the training data due to different weather conditions, object sizes, \\textit{etc}. A key factor in this performance degradation is the diminished generalizability of pre-trained models, which creates a sharp loss landscape during training. Such sharpness, when encountered during testing, can precipitate significant performance declines, even with minor data variations. To address the aforementioned challenges, we propose \\textbf{dual-perturbation optimization (DPO)} for \\textbf{\\underline{T}est-\\underline{t}ime \\underline{A}daptation in \\underline{3}D \\underline{O}bject \\underline{D}etection (TTA-3OD)}. We minimize the sharpness to cultivate a flat loss landscape to ensure model resiliency to minor data variations, thereby enhancing the generalization of the adaptation process. To fully capture the inherent variability of the test point clouds, we further introduce adversarial perturbation to the input BEV features to better simulate the noisy test environment. As the dual perturbation strategy relies on trustworthy supervision signals, we utilize a reliable Hungarian matcher to filter out pseudo-labels sensitive to perturbations. Additionally, we introduce early Hungarian cutoff to avoid error accumulation from incorrect pseudo-labels by halting the adaptation process. Extensive experiments across three types of transfer tasks demonstrate that the proposed DPO significantly surpasses previous state-of-the-art approaches, specifically on Waymo $\\rightarrow$ KITTI, outperforming the most competitive baseline by 57.72\\% in $\\text{AP}_\\text{3D}$ and reaching 91\\% of the fully supervised upper bound.","url_abs":"https://arxiv.org/abs/2406.13891v2","url_pdf":"https://arxiv.org/pdf/2406.13891v2.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":"dpo-dual-perturbation-optimization-for-test","repo_url":"https://github.com/jo-wang/dpo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"test-time-adaptation","task_name":"Test-time Adaptation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"dpo","method_name":"DPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.13891","atlas_url":"https://app.syntology.ai/?focus=2406.13891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13891"}},"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/jo-wang/dpo","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":"44db2351bcc0bffe","entry":"cfg_from_yaml_file","repo":"jo-wang/dpo","repo_kind":"official","path":"pcdet/config.py","file_url":"https://github.com/jo-wang/dpo/blob/HEAD/pcdet/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"44db2351bcc0bffe"}},{"code_sha256_prefix":"1780d388cc532a6d","entry":"get_corner_loss_lidar","repo":"jo-wang/dpo","repo_kind":"official","path":"pcdet/utils/loss_utils.py","file_url":"https://github.com/jo-wang/dpo/blob/HEAD/pcdet/utils/loss_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1780d388cc532a6d"}},{"code_sha256_prefix":"50e8e8cdfc5129f0","entry":"merge_new_config","repo":"jo-wang/dpo","repo_kind":"official","path":"pcdet/config.py","file_url":"https://github.com/jo-wang/dpo/blob/HEAD/pcdet/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50e8e8cdfc5129f0"}},{"code_sha256_prefix":"2b4e0558df870bf9","entry":"post_act_block","repo":"jo-wang/dpo","repo_kind":"official","path":"pcdet/models/backbones_3d/spconv_backbone.py","file_url":"https://github.com/jo-wang/dpo/blob/HEAD/pcdet/models/backbones_3d/spconv_backbone.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b4e0558df870bf9"}},{"code_sha256_prefix":"b69081c0963e2de1","entry":"save_pseudo_label_batch","repo":"jo-wang/dpo","repo_kind":"official","path":"pcdet/tta_methods/dpo.py","file_url":"https://github.com/jo-wang/dpo/blob/HEAD/pcdet/tta_methods/dpo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b69081c0963e2de1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}