{"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/cgnet-a-light-weight-context-guided-network","title":"CGNet: A Light-weight Context Guided Network for Semantic Segmentation","arxiv_id":"1811.08201","date":"2018-11-20","proceeding":null,"authors":["Tianyi Wu","Sheng Tang","Rui Zhang","Yongdong Zhang"],"abstract":"The demand of applying semantic segmentation model on mobile devices has been\nincreasing rapidly. Current state-of-the-art networks have enormous amount of\nparameters hence unsuitable for mobile devices, while other small memory\nfootprint models follow the spirit of classification network and ignore the\ninherent characteristic of semantic segmentation. To tackle this problem, we\npropose a novel Context Guided Network (CGNet), which is a light-weight and\nefficient network for semantic segmentation. We first propose the Context\nGuided (CG) block, which learns the joint feature of both local feature and\nsurrounding context, and further improves the joint feature with the global\ncontext. Based on the CG block, we develop CGNet which captures contextual\ninformation in all stages of the network and is specially tailored for\nincreasing segmentation accuracy. CGNet is also elaborately designed to reduce\nthe number of parameters and save memory footprint. Under an equivalent number\nof parameters, the proposed CGNet significantly outperforms existing\nsegmentation networks. Extensive experiments on Cityscapes and CamVid datasets\nverify the effectiveness of the proposed approach. Specifically, without any\npost-processing and multi-scale testing, the proposed CGNet achieves 64.8% mean\nIoU on Cityscapes with less than 0.5 M parameters. The source code for the\ncomplete system can be found at https://github.com/wutianyiRosun/CGNet.","url_abs":"http://arxiv.org/abs/1811.08201v2","url_pdf":"http://arxiv.org/pdf/1811.08201v2.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":"cgnet-a-light-weight-context-guided-network","repo_url":"https://github.com/wutianyiRosun/CGNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cgnet-a-light-weight-context-guided-network","repo_url":"https://github.com/632652101/CGNet-Pd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok"}},{"paper_slug":"cgnet-a-light-weight-context-guided-network","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":"cgnet-a-light-weight-context-guided-network","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}],"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-eventscape","task":"Semantic Segmentation","dataset":"EventScape","model":"CGNet","rank_in_archive_order":8,"of":12,"metrics":{"mIoU":"44.75"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.08201","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.08201"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/632652101/CGNet-Pd","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zh320/realtime-semantic-segmentation-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/osmr/imgclsmob","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wutianyiRosun/CGNet","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"4ce2b9884c63f4ec","entry":"adjust_learning_rate","repo":"wutianyiRosun/CGNet","repo_kind":"official","path":"cityscapes_train.py","file_url":"https://github.com/wutianyiRosun/CGNet/blob/HEAD/cityscapes_train.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ce2b9884c63f4ec"}},{"code_sha256_prefix":"5a62e086416203cb","entry":"build_blocks","repo":"zh320/realtime-semantic-segmentation-pytorch","repo_kind":"listed","path":"models/cgnet.py","file_url":"https://github.com/zh320/realtime-semantic-segmentation-pytorch/blob/HEAD/models/cgnet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5a62e086416203cb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}