{"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/full-resolution-residual-networks-for","title":"Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes","arxiv_id":"1611.08323","date":"2016-11-24","proceeding":"CVPR 2017 7","authors":["Tobias Pohlen","Alexander Hermans","Markus Mathias","Bastian Leibe"],"abstract":"Semantic image segmentation is an essential component of modern autonomous\ndriving systems, as an accurate understanding of the surrounding scene is\ncrucial to navigation and action planning. Current state-of-the-art approaches\nin semantic image segmentation rely on pre-trained networks that were initially\ndeveloped for classifying images as a whole. While these networks exhibit\noutstanding recognition performance (i.e., what is visible?), they lack\nlocalization accuracy (i.e., where precisely is something located?). Therefore,\nadditional processing steps have to be performed in order to obtain\npixel-accurate segmentation masks at the full image resolution. To alleviate\nthis problem we propose a novel ResNet-like architecture that exhibits strong\nlocalization and recognition performance. We combine multi-scale context with\npixel-level accuracy by using two processing streams within our network: One\nstream carries information at the full image resolution, enabling precise\nadherence to segment boundaries. The other stream undergoes a sequence of\npooling operations to obtain robust features for recognition. The two streams\nare coupled at the full image resolution using residuals. Without additional\nprocessing steps and without pre-training, our approach achieves an\nintersection-over-union score of 71.8% on the Cityscapes dataset.","url_abs":"http://arxiv.org/abs/1611.08323v2","url_pdf":"http://arxiv.org/pdf/1611.08323v2.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":"full-resolution-residual-networks-for","repo_url":"https://github.com/TobyPDE/FRRN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"full-resolution-residual-networks-for","repo_url":"https://github.com/geodekid/frnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"full-resolution-residual-networks-for","repo_url":"https://github.com/jcheunglin/Full-Resolution-Residual-Networks-with-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"full-resolution-residual-networks-for","repo_url":"https://github.com/robin-chan/decision-rules","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes","task":"Real-Time Semantic Segmentation","dataset":"Cityscapes test","model":"FRRN","rank_in_archive_order":26,"of":39,"metrics":{"Frame (fps)":"2.1","Time (ms)":"469","mIoU":"71.8%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"FRRN","rank_in_archive_order":71,"of":105,"metrics":{"Mean IoU (class)":"71.8%"},"uses_additional_data":false},{"leaderboard":"/sota/thermal-image-segmentation-on-mfn-dataset","task":"Thermal Image Segmentation","dataset":"MFN Dataset","model":"FRRN","rank_in_archive_order":50,"of":55,"metrics":{"mIOU":"44.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1611.08323","atlas_url":"https://app.syntology.ai/?focus=1611.08323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.08323"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/TobyPDE/FRRN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/robin-chan/decision-rules","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jcheunglin/Full-Resolution-Residual-Networks-with-PyTorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/geodekid/frnn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"listed":{"samples":2,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"546ed48237afede3","entry":"frr_func","repo":"jcheunglin/Full-Resolution-Residual-Networks-with-PyTorch","repo_kind":"listed","path":"FRRNet.py","file_url":"https://github.com/jcheunglin/Full-Resolution-Residual-Networks-with-PyTorch/blob/HEAD/FRRNet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"546ed48237afede3"}},{"code_sha256_prefix":"b1550953d64b2d7c","entry":"residual_func","repo":"jcheunglin/Full-Resolution-Residual-Networks-with-PyTorch","repo_kind":"listed","path":"FRRNet.py","file_url":"https://github.com/jcheunglin/Full-Resolution-Residual-Networks-with-PyTorch/blob/HEAD/FRRNet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b1550953d64b2d7c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}