{"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/training-of-convolutional-networks-on","title":"Training of Convolutional Networks on Multiple Heterogeneous Datasets for Street Scene Semantic Segmentation","arxiv_id":"1803.05675","date":"2018-03-15","proceeding":null,"authors":["Panagiotis Meletis","Gijs Dubbelman"],"abstract":"We propose a convolutional network with hierarchical classifiers for\nper-pixel semantic segmentation, which is able to be trained on multiple,\nheterogeneous datasets and exploit their semantic hierarchy. Our network is the\nfirst to be simultaneously trained on three different datasets from the\nintelligent vehicles domain, i.e. Cityscapes, GTSDB and Mapillary Vistas, and\nis able to handle different semantic level-of-detail, class imbalances, and\ndifferent annotation types, i.e. dense per-pixel and sparse bounding-box\nlabels. We assess our hierarchical approach, by comparing against flat,\nnon-hierarchical classifiers and we show improvements in mean pixel accuracy of\n13.0% for Cityscapes classes and 2.4% for Vistas classes and 32.3% for GTSDB\nclasses. Our implementation achieves inference rates of 17 fps at a resolution\nof 520x706 for 108 classes running on a GPU.","url_abs":"http://arxiv.org/abs/1803.05675v2","url_pdf":"http://arxiv.org/pdf/1803.05675v2.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":"training-of-convolutional-networks-on","repo_url":"https://github.com/pmeletis/hierarchical-semantic-segmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"training-of-convolutional-networks-on","repo_url":"https://github.com/pmeletis/IV2018-hierarchical-semantic-segmentation-for-heterogeneous-datasets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-kitti-semantic","task":"Semantic Segmentation","dataset":"KITTI Semantic Segmentation","model":"AHiSS","rank_in_archive_order":5,"of":7,"metrics":{"Mean IoU (class)":"61.24"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.05675","atlas_url":"https://app.syntology.ai/?focus=1803.05675","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":"1803.05675"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1803.05675\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1803.05675"},"call":"get_concepts_for_paper(arxiv_id=\"1803.05675\")"}],"by_repo":[{"repo":"pmeletis/hierarchical-semantic-segmentation","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"pmeletis/IV2018-hierarchical-semantic-segmentation-for-heterogeneous-datasets","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":"7278e0d9761639fb34f04b82d312864e87bc5057f02be7430dcd73afc6761eb6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}