{"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/icnet-for-real-time-semantic-segmentation-on","title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","arxiv_id":"1704.08545","date":"2017-04-27","proceeding":"ECCV 2018 9","authors":["Hengshuang Zhao","Xiaojuan Qi","Xiaoyong Shen","Jianping Shi","Jiaya Jia"],"abstract":"We focus on the challenging task of real-time semantic segmentation in this\npaper. It finds many practical applications and yet is with fundamental\ndifficulty of reducing a large portion of computation for pixel-wise label\ninference. We propose an image cascade network (ICNet) that incorporates\nmulti-resolution branches under proper label guidance to address this\nchallenge. We provide in-depth analysis of our framework and introduce the\ncascade feature fusion unit to quickly achieve high-quality segmentation. Our\nsystem yields real-time inference on a single GPU card with decent quality\nresults evaluated on challenging datasets like Cityscapes, CamVid and\nCOCO-Stuff.","url_abs":"http://arxiv.org/abs/1704.08545v2","url_pdf":"http://arxiv.org/pdf/1704.08545v2.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":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/hszhao/ICNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/Bigpingping97/ICNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/GuangyanZhang/SCNN-Deeplabv3-bisenet-icnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok"}},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/Mind23-2/MindCode-53","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/daheyinyin/ICNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/hellochick/ICNet-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/liminn/icnet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/lisilin013/ICNet-tensorflow-ros","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/lyqcom/icnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/mattangus/fast-semantic-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/oandrienko/fast-semantic-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/pooruss/ICNet-Paddle2.2.0rc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"unanswered"}},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/victorpham1997/Local_ICNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/zh320/realtime-semantic-segmentation-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/Mind23-2/MindCode-3/tree/main/ICNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/mindspore-ai/models/tree/master/research/cv/ICNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"icnet-for-real-time-semantic-segmentation-on","repo_url":"https://github.com/yfjcode/ICNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"dichotomous-image-segmentation","task_name":"Dichotomous Image Segmentation"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"real-time-semantic-segmentation","task_name":"Real-Time Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"thermal-image-segmentation","task_name":"Thermal Image Segmentation"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te1","task":"Dichotomous Image Segmentation","dataset":"DIS-TE1","model":"ICNet","rank_in_archive_order":17,"of":22,"metrics":{"E-measure":"0.784","HCE":"234","MAE":"0.095","S-Measure":"0.716","max F-Measure":"0.631","weighted F-measure":"0.535"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te2","task":"Dichotomous Image Segmentation","dataset":"DIS-TE2","model":"ICNet","rank_in_archive_order":15,"of":22,"metrics":{"E-measure":"0.826","HCE":"512","MAE":"0.095","S-Measure":"0.759","max F-Measure":"0.716","weighted F-measure":"0.627"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te3","task":"Dichotomous Image Segmentation","dataset":"DIS-TE3","model":"ICNet","rank_in_archive_order":12,"of":22,"metrics":{"E-measure":"0.852","HCE":"1001","MAE":"0.091","S-Measure":"0.780","max F-Measure":"0.752","weighted F-measure":"0.664"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te4","task":"Dichotomous Image Segmentation","dataset":"DIS-TE4","model":"ICNet","rank_in_archive_order":12,"of":22,"metrics":{"E-measure":"0.837","HCE":"3690","MAE":"0.099","S-Measure":"0.776","max F-Measure":"0.749","weighted F-measure":"0.663"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-vd","task":"Dichotomous Image Segmentation","dataset":"DIS-VD","model":"ICNet","rank_in_archive_order":14,"of":24,"metrics":{"E-measure":"0.811","HCE":"1503","MAE":"0.102","S-Measure":"0.747","max F-Measure":"0.697","weighted F-measure":"0.609"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-semantic-segmentation-on-camvid","task":"Real-Time Semantic Segmentation","dataset":"CamVid","model":"ICNet","rank_in_archive_order":23,"of":29,"metrics":{"Frame (fps)":"27.8","Time (ms)":"36","mIoU":"67.1%"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes","task":"Real-Time Semantic Segmentation","dataset":"Cityscapes test","model":"ICNet","rank_in_archive_order":31,"of":39,"metrics":{"Frame (fps)":"30.3","Time (ms)":"33","mIoU":"70.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-bdd100k-val","task":"Semantic Segmentation","dataset":"BDD100K val","model":"ICNet","rank_in_archive_order":13,"of":24,"metrics":{"mIoU":"52.4(39.5fps)"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"ICNet","rank_in_archive_order":79,"of":105,"metrics":{"Mean IoU (class)":"70.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-trans10k","task":"Semantic Segmentation","dataset":"Trans10K","model":"ICNet","rank_in_archive_order":14,"of":15,"metrics":{"GFLOPs":"10.64","mIoU":"23.39%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.08545","atlas_url":"https://app.syntology.ai/?focus=1704.08545","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":"1704.08545"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1704.08545\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1704.08545"},"call":"get_concepts_for_paper(arxiv_id=\"1704.08545\")"}],"by_repo":[{"repo":"hszhao/ICNet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Bigpingping97/ICNet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"GuangyanZhang/SCNN-Deeplabv3-bisenet-icnet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Mind23-2/MindCode-53","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"daheyinyin/ICNet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"hellochick/ICNet-tensorflow","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"liminn/icnet-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lisilin013/ICNet-tensorflow-ros","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lyqcom/icnet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"mattangus/fast-semantic-segmentation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"oandrienko/fast-semantic-segmentation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"osmr/imgclsmob","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2004.08955"],"harvested_for_calls":[{"arxiv_id":"2004.08955","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.08955"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.08955\")"}]},{"repo":"pooruss/ICNet-Paddle2.2.0rc","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"victorpham1997/Local_ICNet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"zh320/realtime-semantic-segmentation-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1811.08201","1811.11431","2104.06403","2104.13188"],"harvested_for_calls":[{"arxiv_id":"1811.08201","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1811.08201"},"call":"get_harvested_code_for_paper(arxiv_id=\"1811.08201\")"},{"arxiv_id":"1811.11431","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1811.11431"},"call":"get_harvested_code_for_paper(arxiv_id=\"1811.11431\")"},{"arxiv_id":"2104.06403","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.06403"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.06403\")"},{"arxiv_id":"2104.13188","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.13188"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.13188\")"}]},{"repo":"Mind23-2/MindCode-3","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"mindspore-ai/models","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2208.08084"],"harvested_for_calls":[{"arxiv_id":"2208.08084","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2208.08084"},"call":"get_harvested_code_for_paper(arxiv_id=\"2208.08084\")"}]},{"repo":"yfjcode/ICNet","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":"493e0fc1e14e4996e9a0e89d05b609847917e1f0bd983c46e5d19d984d942e38","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}