{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/focalformer3d-focusing-on-hard-instance-for","title":"FocalFormer3D : Focusing on Hard Instance for 3D Object Detection","arxiv_id":"2308.04556","date":"2023-08-08","proceeding":null,"authors":["Yilun Chen","Zhiding Yu","Yukang Chen","Shiyi Lan","Animashree Anandkumar","Jiaya Jia","Jose Alvarez"],"abstract":"False negatives (FN) in 3D object detection, {\\em e.g.}, missing predictions of pedestrians, vehicles, or other obstacles, can lead to potentially dangerous situations in autonomous driving. While being fatal, this issue is understudied in many current 3D detection methods. In this work, we propose Hard Instance Probing (HIP), a general pipeline that identifies \\textit{FN} in a multi-stage manner and guides the models to focus on excavating difficult instances. For 3D object detection, we instantiate this method as FocalFormer3D, a simple yet effective detector that excels at excavating difficult objects and improving prediction recall. FocalFormer3D features a multi-stage query generation to discover hard objects and a box-level transformer decoder to efficiently distinguish objects from massive object candidates. Experimental results on the nuScenes and Waymo datasets validate the superior performance of FocalFormer3D. The advantage leads to strong performance on both detection and tracking, in both LiDAR and multi-modal settings. Notably, FocalFormer3D achieves a 70.5 mAP and 73.9 NDS on nuScenes detection benchmark, while the nuScenes tracking benchmark shows 72.1 AMOTA, both ranking 1st place on the nuScenes LiDAR leaderboard. Our code is available at \\url{https://github.com/NVlabs/FocalFormer3D}.","url_abs":"https://arxiv.org/abs/2308.04556v1","url_pdf":"https://arxiv.org/pdf/2308.04556v1.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":"focalformer3d-focusing-on-hard-instance-for","repo_url":"https://github.com/NVlabs/FocalFormer3D","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"decoder","task_name":"Decoder"},{"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":[{"leaderboard":"/sota/3d-object-detection-on-nuscenes","task":"3D Object Detection","dataset":"nuScenes","model":"FocalFormer3D-F","rank_in_archive_order":11,"of":372,"metrics":{"NDS":"0.75","mAAE":"0.13","mAOE":"0.33","mAP":"0.72","mASE":"0.24","mATE":"0.25","mAVE":"0.23"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-nuscenes","task":"3D Object Detection","dataset":"nuScenes","model":"FocalFormer3D-TTA","rank_in_archive_order":21,"of":372,"metrics":{"NDS":"0.74","mAAE":"0.13","mAOE":"0.32","mAP":"0.71","mASE":"0.24","mATE":"0.24","mAVE":"0.20"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-nuscenes","task":"3D Object Detection","dataset":"nuScenes","model":"FocalFormer3D-L","rank_in_archive_order":40,"of":372,"metrics":{"NDS":"0.73","mAAE":"0.13","mAOE":"0.34","mAP":"0.69","mASE":"0.24","mATE":"0.25","mAVE":"0.22"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.04556","atlas_url":"https://app.syntology.ai/?focus=2308.04556","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2308.04556"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2308.04556\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2308.04556"},"call":"get_concepts_for_paper(arxiv_id=\"2308.04556\")"}],"by_repo":[{"repo":"NVlabs/FocalFormer3D","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ebb455feb676cf05a3c7f0cf8ed87a0b87b275c235c5f4adb43812197b56fdb4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}