{"about":{"site":"https://codewithpapers.app","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.","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"},"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":{"atlas_url":"https://app.syntology.ai/?focus=1703.02719","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}