{"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/conditional-random-fields-as-recurrent-neural-1","title":"Conditional Random Fields as Recurrent Neural Networks","arxiv_id":"1502.03240","date":"2015-02-11","proceeding":"ICCV 2015 12","authors":["Shuai Zheng","Sadeep Jayasumana","Bernardino Romera-Paredes","Vibhav Vineet","Zhizhong Su","Dalong Du","Chang Huang","Philip H. S. Torr"],"abstract":"Pixel-level labelling tasks, such as semantic segmentation, play a central\nrole in image understanding. Recent approaches have attempted to harness the\ncapabilities of deep learning techniques for image recognition to tackle\npixel-level labelling tasks. One central issue in this methodology is the\nlimited capacity of deep learning techniques to delineate visual objects. To\nsolve this problem, we introduce a new form of convolutional neural network\nthat combines the strengths of Convolutional Neural Networks (CNNs) and\nConditional Random Fields (CRFs)-based probabilistic graphical modelling. To\nthis end, we formulate mean-field approximate inference for the Conditional\nRandom Fields with Gaussian pairwise potentials as Recurrent Neural Networks.\nThis network, called CRF-RNN, is then plugged in as a part of a CNN to obtain a\ndeep network that has desirable properties of both CNNs and CRFs. Importantly,\nour system fully integrates CRF modelling with CNNs, making it possible to\ntrain the whole deep network end-to-end with the usual back-propagation\nalgorithm, avoiding offline post-processing methods for object delineation. We\napply the proposed method to the problem of semantic image segmentation,\nobtaining top results on the challenging Pascal VOC 2012 segmentation\nbenchmark.","url_abs":"http://arxiv.org/abs/1502.03240v3","url_pdf":"http://arxiv.org/pdf/1502.03240v3.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":"conditional-random-fields-as-recurrent-neural-1","repo_url":"https://github.com/torrvision/crfasrnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"conditional-random-fields-as-recurrent-neural-1","repo_url":"https://github.com/AsafBarZvi/Liver_project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"conditional-random-fields-as-recurrent-neural-1","repo_url":"https://github.com/MiguelMonteiro/CRFasRNNLayer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"conditional-random-fields-as-recurrent-neural-1","repo_url":"https://github.com/liyin2015/superpixel_crfasrnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"conditional-random-fields-as-recurrent-neural-1","repo_url":"https://github.com/sadeepj/crfasrnn_keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"conditional-random-fields-as-recurrent-neural-1","repo_url":"https://github.com/sadeepj/crfasrnn_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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"}],"methods":[{"method_slug":"crf","method_name":"CRF"},{"method_slug":"crf-rnn","method_name":"CRF-RNN"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fcn","method_name":"FCN"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"sgd-with-momentum","method_name":"SGD with Momentum"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[{"slug":"crf-rnn","name":"CRF-RNN","full_name":"CRF-RNN"}],"results":[{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes","task":"Real-Time Semantic Segmentation","dataset":"Cityscapes test","model":"CRF-RNN","rank_in_archive_order":38,"of":39,"metrics":{"Frame (fps)":"1.4","Time (ms)":"700","mIoU":"62.5%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-context","task":"Semantic Segmentation","dataset":"PASCAL Context","model":"CRF-RNN","rank_in_archive_order":62,"of":66,"metrics":{"mIoU":"39.3"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"CRF-RNN","rank_in_archive_order":36,"of":51,"metrics":{"Mean IoU":"74.7%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1502.03240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1502.03240"}},"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/sadeepj/crfasrnn_keras","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sadeepj/crfasrnn_pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/torrvision/crfasrnn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MiguelMonteiro/CRFasRNNLayer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AsafBarZvi/Liver_project","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liyin2015/superpixel_crfasrnn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"unverified":7},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1},"listed":{"samples":6,"ran":0,"repositories":3}},"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":2,"samples":[{"code_sha256_prefix":"31e46c827e832dd6","entry":"resize_image","repo":"torrvision/crfasrnn","repo_kind":"official","path":"python-scripts/crfasrnn_demo.py","file_url":"https://github.com/torrvision/crfasrnn/blob/HEAD/python-scripts/crfasrnn_demo.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"31e46c827e832dd6"}},{"code_sha256_prefix":"db38aa03e6d3a208","entry":"get_label_image","repo":"liyin2015/superpixel_crfasrnn","repo_kind":"listed","path":"src/util.py","file_url":"https://github.com/liyin2015/superpixel_crfasrnn/blob/HEAD/src/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"db38aa03e6d3a208"}},{"code_sha256_prefix":"009195585f116fc3","entry":"get_label_image","repo":"sadeepj/crfasrnn_keras","repo_kind":"listed","path":"src/util.py","file_url":"https://github.com/sadeepj/crfasrnn_keras/blob/HEAD/src/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"009195585f116fc3"}},{"code_sha256_prefix":"9155576698e42614","entry":"get_label_image","repo":"sadeepj/crfasrnn_pytorch","repo_kind":"listed","path":"crfasrnn/util.py","file_url":"https://github.com/sadeepj/crfasrnn_pytorch/blob/HEAD/crfasrnn/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9155576698e42614"}},{"code_sha256_prefix":"fc71619ee0d554fe","entry":"get_palette","repo":"torrvision/crfasrnn","repo_kind":"official","path":"python-scripts/crfasrnn_demo.py","file_url":"https://github.com/torrvision/crfasrnn/blob/HEAD/python-scripts/crfasrnn_demo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"fc71619ee0d554fe"}},{"code_sha256_prefix":"54e90a3f29d4b02d","entry":"get_preprocessed_image","repo":"liyin2015/superpixel_crfasrnn","repo_kind":"listed","path":"src/util.py","file_url":"https://github.com/liyin2015/superpixel_crfasrnn/blob/HEAD/src/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"54e90a3f29d4b02d"}},{"code_sha256_prefix":"9c0f9edd8720acc3","entry":"get_preprocessed_image","repo":"sadeepj/crfasrnn_keras","repo_kind":"listed","path":"src/util.py","file_url":"https://github.com/sadeepj/crfasrnn_keras/blob/HEAD/src/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9c0f9edd8720acc3"}},{"code_sha256_prefix":"a8826ad32226c0b9","entry":"get_preprocessed_image","repo":"sadeepj/crfasrnn_pytorch","repo_kind":"listed","path":"crfasrnn/util.py","file_url":"https://github.com/sadeepj/crfasrnn_pytorch/blob/HEAD/crfasrnn/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a8826ad32226c0b9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}