{"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/large-kernel-matters-improve-semantic","title":"Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network","arxiv_id":"1703.02719","date":"2017-03-08","proceeding":"CVPR 2017 7","authors":["Chao Peng","Xiangyu Zhang","Gang Yu","Guiming Luo","Jian Sun"],"abstract":"One of recent trends [30, 31, 14] in network architec- ture design is\nstacking small filters (e.g., 1x1 or 3x3) in the entire network because the\nstacked small filters is more ef- ficient than a large kernel, given the same\ncomputational complexity. However, in the field of semantic segmenta- tion,\nwhere we need to perform dense per-pixel prediction, we find that the large\nkernel (and effective receptive field) plays an important role when we have to\nperform the clas- sification and localization tasks simultaneously. Following\nour design principle, we propose a Global Convolutional Network to address both\nthe classification and localization issues for the semantic segmentation. We\nalso suggest a residual-based boundary refinement to further refine the ob-\nject boundaries. Our approach achieves state-of-art perfor- mance on two public\nbenchmarks and significantly outper- forms previous results, 82.2% (vs 80.2%)\non PASCAL VOC 2012 dataset and 76.9% (vs 71.8%) on Cityscapes dataset.","url_abs":"http://arxiv.org/abs/1703.02719v1","url_pdf":"http://arxiv.org/pdf/1703.02719v1.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":"large-kernel-matters-improve-semantic","repo_url":"https://github.com/preritj/segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"large-kernel-matters-improve-semantic","repo_url":"https://github.com/y-ouali/pytorch_segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"global-convolutional-network","method_name":"Global Convolutional Network"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[{"slug":"global-convolutional-network","name":"Global Convolutional Network","full_name":"Global Convolutional Network"}],"results":[{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"Large Kernel Matters","rank_in_archive_order":17,"of":51,"metrics":{"Mean IoU":"83.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012-val","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"ResNet-GCN","rank_in_archive_order":8,"of":29,"metrics":{"mIoU":"81.0%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1703.02719","atlas_url":"https://app.syntology.ai/?focus=1703.02719","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":"1703.02719"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1703.02719\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1703.02719"},"call":"get_concepts_for_paper(arxiv_id=\"1703.02719\")"}],"by_repo":[{"repo":"preritj/segmentation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1505.04597"],"harvested_for_calls":[{"arxiv_id":"1505.04597","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1505.04597"},"call":"get_harvested_code_for_paper(arxiv_id=\"1505.04597\")"}]},{"repo":"y-ouali/pytorch_segmentation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"3c6b3027267a74b4e4eb7232e4a6ce0da17e9cb5e7adb1f4ad03b4e3b7bc103e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}