{"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/lars-a-diverse-panoptic-maritime-obstacle","title":"LaRS: A Diverse Panoptic Maritime Obstacle Detection Dataset and Benchmark","arxiv_id":"2308.09618","date":"2023-08-18","proceeding":"ICCV 2023 1","authors":["Lojze Žust","Janez Perš","Matej Kristan"],"abstract":"The progress in maritime obstacle detection is hindered by the lack of a diverse dataset that adequately captures the complexity of general maritime environments. We present the first maritime panoptic obstacle detection benchmark LaRS, featuring scenes from Lakes, Rivers and Seas. Our major contribution is the new dataset, which boasts the largest diversity in recording locations, scene types, obstacle classes, and acquisition conditions among the related datasets. LaRS is composed of over 4000 per-pixel labeled key frames with nine preceding frames to allow utilization of the temporal texture, amounting to over 40k frames. Each key frame is annotated with 8 thing, 3 stuff classes and 19 global scene attributes. We report the results of 27 semantic and panoptic segmentation methods, along with several performance insights and future research directions. To enable objective evaluation, we have implemented an online evaluation server. The LaRS dataset, evaluation toolkit and benchmark are publicly available at: https://lojzezust.github.io/lars-dataset","url_abs":"https://arxiv.org/abs/2308.09618v1","url_pdf":"https://arxiv.org/pdf/2308.09618v1.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":"lars-a-diverse-panoptic-maritime-obstacle","repo_url":"https://github.com/lojzezust/mmsegmentation-macvi","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"lars-a-diverse-panoptic-maritime-obstacle","repo_url":"https://github.com/lojzezust/lars_evaluator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"lars","name":"LaRS","full_name":"Lakes, Rivers and Seas Dataset"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/panoptic-segmentation-on-lars","task":"Panoptic Segmentation","dataset":"LaRS","model":"Mask2Former (Swin-B)","rank_in_archive_order":1,"of":8,"metrics":{"PQ":"41.7"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-lars","task":"Panoptic Segmentation","dataset":"LaRS","model":"Panoptic FPN (ResNet-50)","rank_in_archive_order":2,"of":8,"metrics":{"PQ":"40.1"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-lars","task":"Panoptic Segmentation","dataset":"LaRS","model":"Mask2Former (Swin-T)","rank_in_archive_order":3,"of":8,"metrics":{"PQ":"39.2"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-lars","task":"Panoptic Segmentation","dataset":"LaRS","model":"Panoptic FPN (ResNet-101)","rank_in_archive_order":4,"of":8,"metrics":{"PQ":"38.7"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-lars","task":"Panoptic Segmentation","dataset":"LaRS","model":"Mask2Former (ResNet-50)","rank_in_archive_order":5,"of":8,"metrics":{"PQ":"37.6"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-lars","task":"Panoptic Segmentation","dataset":"LaRS","model":"Mask2Former (ResNet-101)","rank_in_archive_order":6,"of":8,"metrics":{"PQ":"37.2"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-lars","task":"Panoptic Segmentation","dataset":"LaRS","model":"Panoptic Deeplab (ResNet-50)","rank_in_archive_order":7,"of":8,"metrics":{"PQ":"34.7"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-lars","task":"Panoptic Segmentation","dataset":"LaRS","model":"MaX-DeepLab","rank_in_archive_order":8,"of":8,"metrics":{"PQ":"31.9"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-lars","task":"Semantic Segmentation","dataset":"LaRS","model":"KNet (Swin-T)","rank_in_archive_order":4,"of":20,"metrics":{"F1":"73.4","Q":"71.3","mIoU":"97.2","μ":"78.8"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-lars","task":"Semantic Segmentation","dataset":"LaRS","model":"SegFormer (MiT-B2)","rank_in_archive_order":5,"of":20,"metrics":{"F1":"70.0","Q":"67.8","mIoU":"96.8","μ":"78.6"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-lars","task":"Semantic Segmentation","dataset":"LaRS","model":"DeepLabv3 (ResNet-101)","rank_in_archive_order":6,"of":20,"metrics":{"F1":"66.1","Q":"62.9","mIoU":"95.2","μ":"77.5"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-lars","task":"Semantic Segmentation","dataset":"LaRS","model":"PointRend","rank_in_archive_order":7,"of":20,"metrics":{"F1":"65.4","Q":"62.1","mIoU":"94.9","μ":"77.5"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-lars","task":"Semantic Segmentation","dataset":"LaRS","model":"DeepLabv3+ (ResNet-101)","rank_in_archive_order":8,"of":20,"metrics":{"F1":"64.0","Q":"61.0","mIoU":"95.4","μ":"77.8"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-lars","task":"Semantic Segmentation","dataset":"LaRS","model":"STDC2","rank_in_archive_order":9,"of":20,"metrics":{"F1":"64.3","Q":"60.8","mIoU":"94.5","μ":"76.5"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-lars","task":"Semantic Segmentation","dataset":"LaRS","model":"FCN (ResNet-101)","rank_in_archive_order":10,"of":20,"metrics":{"F1":"63.4","Q":"60.2","mIoU":"95.0","μ":"77.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-lars","task":"Semantic Segmentation","dataset":"LaRS","model":"WaSR (ResNet-101)","rank_in_archive_order":11,"of":20,"metrics":{"F1":"61.6","Q":"59.5","mIoU":"96.6","μ":"71.0"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-lars","task":"Semantic Segmentation","dataset":"LaRS","model":"STDC1","rank_in_archive_order":12,"of":20,"metrics":{"F1":"61.8","Q":"57.8","mIoU":"93.6","μ":"75.6"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-lars","task":"Semantic Segmentation","dataset":"LaRS","model":"FCN (ResNet-50)","rank_in_archive_order":14,"of":20,"metrics":{"F1":"57.9","Q":"53.6","mIoU":"92.6","μ":"76.8"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-lars","task":"Semantic Segmentation","dataset":"LaRS","model":"Segmenter (ViT-B)","rank_in_archive_order":15,"of":20,"metrics":{"F1":"55.2","Q":"52.6","mIoU":"95.1","μ":"72.2"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-lars","task":"Semantic Segmentation","dataset":"LaRS","model":"BiSeNetv2","rank_in_archive_order":16,"of":20,"metrics":{"F1":"54.7","Q":"51.2","mIoU":"93.5","μ":"73.9"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-lars","task":"Semantic Segmentation","dataset":"LaRS","model":"WODIS (ResNet-101)","rank_in_archive_order":17,"of":20,"metrics":{"F1":"47.5","Q":"40.7","mIoU":"85.7","μ":"63.0"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-lars","task":"Semantic Segmentation","dataset":"LaRS","model":"BiSeNetv1 (ResNet-50)","rank_in_archive_order":18,"of":20,"metrics":{"F1":"42.8","Q":"39.4","mIoU":"92.2","μ":"73.3"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-lars","task":"Semantic Segmentation","dataset":"LaRS","model":"IntCatchAI","rank_in_archive_order":19,"of":20,"metrics":{"F1":"44.9","Q":"20.5","mIoU":"45.6","μ":"62.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-lars","task":"Semantic Segmentation","dataset":"LaRS","model":"UNet","rank_in_archive_order":20,"of":20,"metrics":{"F1":"15.4","Q":"13.9","mIoU":"90.1","μ":"75.7"},"uses_additional_data":false},{"leaderboard":"/sota/video-semantic-segmentation-on-lars","task":"Video Semantic Segmentation","dataset":"LaRS","model":"WaSR-T (ResNet-101)","rank_in_archive_order":1,"of":3,"metrics":{"F1":"62.1","Q":"60.1","mIoU":"96.7","μ":"71.1"},"uses_additional_data":false},{"leaderboard":"/sota/video-semantic-segmentation-on-lars","task":"Video Semantic Segmentation","dataset":"LaRS","model":"TMANet (ResNet-50)","rank_in_archive_order":2,"of":3,"metrics":{"F1":"61.1","Q":"57.5","mIoU":"94.1","μ":"77.1"},"uses_additional_data":false},{"leaderboard":"/sota/video-semantic-segmentation-on-lars","task":"Video Semantic Segmentation","dataset":"LaRS","model":"CSANet (ResNet-101)","rank_in_archive_order":3,"of":3,"metrics":{"F1":"52.1","Q":"49.1","mIoU":"94.2","μ":"63.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.09618","atlas_url":"https://app.syntology.ai/?focus=2308.09618","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":"2308.09618"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2308.09618\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2308.09618"},"call":"get_concepts_for_paper(arxiv_id=\"2308.09618\")"}],"by_repo":[{"repo":"lojzezust/mmsegmentation-macvi","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lojzezust/lars_evaluator","kind":"listed","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":"e5f07f720b07c7167379965bae63d6d881865f5b40e3d6172da8b79a29facbb8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}