{"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/parsenet-looking-wider-to-see-better","title":"ParseNet: Looking Wider to See Better","arxiv_id":"1506.04579","date":"2015-06-15","proceeding":null,"authors":["Wei Liu","Andrew Rabinovich","Alexander C. Berg"],"abstract":"We present a technique for adding global context to deep convolutional\nnetworks for semantic segmentation. The approach is simple, using the average\nfeature for a layer to augment the features at each location. In addition, we\nstudy several idiosyncrasies of training, significantly increasing the\nperformance of baseline networks (e.g. from FCN). When we add our proposed\nglobal feature, and a technique for learning normalization parameters, accuracy\nincreases consistently even over our improved versions of the baselines. Our\nproposed approach, ParseNet, achieves state-of-the-art performance on SiftFlow\nand PASCAL-Context with small additional computational cost over baselines, and\nnear current state-of-the-art performance on PASCAL VOC 2012 semantic\nsegmentation with a simple approach. Code is available at\nhttps://github.com/weiliu89/caffe/tree/fcn .","url_abs":"http://arxiv.org/abs/1506.04579v2","url_pdf":"http://arxiv.org/pdf/1506.04579v2.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":"parsenet-looking-wider-to-see-better","repo_url":"https://github.com/weiliu89/caffe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"parsenet-looking-wider-to-see-better","repo_url":"https://github.com/tensorflow/models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"parsenet-looking-wider-to-see-better","repo_url":"https://github.com/tensorflow/models/tree/master/research/deeplab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"parsenet-looking-wider-to-see-better","repo_url":"https://github.com/xiamenwcy/extended-caffe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-pascal-context","task":"Semantic Segmentation","dataset":"PASCAL Context","model":"ParseNet","rank_in_archive_order":61,"of":66,"metrics":{"mIoU":"40.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"ParseNet","rank_in_archive_order":39,"of":51,"metrics":{"Mean IoU":"69.8%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1506.04579","atlas_url":"https://app.syntology.ai/?focus=1506.04579","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}