{"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/seabird-segmentation-in-bird-s-view-with-dice","title":"SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects","arxiv_id":"2403.20318","date":"2024-03-29","proceeding":"CVPR 2024 1","authors":["Abhinav Kumar","Yuliang Guo","Xinyu Huang","Liu Ren","Xiaoming Liu"],"abstract":"Monocular 3D detectors achieve remarkable performance on cars and smaller objects. However, their performance drops on larger objects, leading to fatal accidents. Some attribute the failures to training data scarcity or their receptive field requirements of large objects. In this paper, we highlight this understudied problem of generalization to large objects. We find that modern frontal detectors struggle to generalize to large objects even on nearly balanced datasets. We argue that the cause of failure is the sensitivity of depth regression losses to noise of larger objects. To bridge this gap, we comprehensively investigate regression and dice losses, examining their robustness under varying error levels and object sizes. We mathematically prove that the dice loss leads to superior noise-robustness and model convergence for large objects compared to regression losses for a simplified case. Leveraging our theoretical insights, we propose SeaBird (Segmentation in Bird's View) as the first step towards generalizing to large objects. SeaBird effectively integrates BEV segmentation on foreground objects for 3D detection, with the segmentation head trained with the dice loss. SeaBird achieves SoTA results on the KITTI-360 leaderboard and improves existing detectors on the nuScenes leaderboard, particularly for large objects. Code and models at https://github.com/abhi1kumar/SeaBird","url_abs":"https://arxiv.org/abs/2403.20318v1","url_pdf":"https://arxiv.org/pdf/2403.20318v1.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":"seabird-segmentation-in-bird-s-view-with-dice","repo_url":"https://github.com/abhi1kumar/seabird","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":"3d-object-detection-from-monocular-images","task_name":"3D Object Detection From Monocular Images"},{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"bev-segmentation","task_name":"BEV Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"dice-loss","method_name":"Dice Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-detection-on-nuscenes-camera-only","task":"3D Object Detection","dataset":"nuScenes Camera Only","model":"SeaBird","rank_in_archive_order":14,"of":19,"metrics":{"Future Frame":"false","NDS":"59.7"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-from-monocular-images-on-7","task":"3D Object Detection From Monocular Images","dataset":"KITTI-360","model":"SeaBird + PanopticBEV","rank_in_archive_order":1,"of":11,"metrics":{"AP25":"37.12","AP50":"4.64"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-from-monocular-images-on-7","task":"3D Object Detection From Monocular Images","dataset":"KITTI-360","model":"SeaBird + Image2Maps","rank_in_archive_order":4,"of":11,"metrics":{"AP25":"35.04","AP50":"3.14"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.20318","atlas_url":"https://app.syntology.ai/?focus=2403.20318","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":"2403.20318"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2403.20318\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2403.20318"},"call":"get_concepts_for_paper(arxiv_id=\"2403.20318\")"}],"by_repo":[{"repo":"abhi1kumar/seabird","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2207.10758"],"harvested_for_calls":[{"arxiv_id":"2207.10758","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2207.10758"},"call":"get_harvested_code_for_paper(arxiv_id=\"2207.10758\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"eed363d3a02aa85b4e3024a7709b78209fa1074710f685b15eae6ef19e5f7bdb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}