{"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/efficient-piecewise-training-of-deep","title":"Efficient piecewise training of deep structured models for semantic segmentation","arxiv_id":"1504.01013","date":"2015-04-04","proceeding":"CVPR 2016 6","authors":["Guosheng Lin","Chunhua Shen","Anton van dan Hengel","Ian Reid"],"abstract":"Recent advances in semantic image segmentation have mostly been achieved by\ntraining deep convolutional neural networks (CNNs). We show how to improve\nsemantic segmentation through the use of contextual information; specifically,\nwe explore `patch-patch' context between image regions, and `patch-background'\ncontext. For learning from the patch-patch context, we formulate Conditional\nRandom Fields (CRFs) with CNN-based pairwise potential functions to capture\nsemantic correlations between neighboring patches. Efficient piecewise training\nof the proposed deep structured model is then applied to avoid repeated\nexpensive CRF inference for back propagation. For capturing the\npatch-background context, we show that a network design with traditional\nmulti-scale image input and sliding pyramid pooling is effective for improving\nperformance. Our experimental results set new state-of-the-art performance on a\nnumber of popular semantic segmentation datasets, including NYUDv2, PASCAL VOC\n2012, PASCAL-Context, and SIFT-flow. In particular, we achieve an\nintersection-over-union score of 78.0 on the challenging PASCAL VOC 2012\ndataset.","url_abs":"http://arxiv.org/abs/1504.01013v4","url_pdf":"http://arxiv.org/pdf/1504.01013v4.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":[],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"crf","method_name":"CRF"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"Context","rank_in_archive_order":73,"of":105,"metrics":{"Mean IoU (class)":"71.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-context","task":"Semantic Segmentation","dataset":"PASCAL Context","model":"Piecewise","rank_in_archive_order":57,"of":66,"metrics":{"mIoU":"43.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1504.01013","atlas_url":"https://app.syntology.ai/?focus=1504.01013","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":"1504.01013"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1504.01013\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1504.01013"},"call":"get_concepts_for_paper(arxiv_id=\"1504.01013\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b5ec68b11433188fe0c1f0da91649eb3a351c6a70c4ffc19860d7d6d4764a8d0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}