{"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/deep-value-networks-learn-to-evaluate-and","title":"Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs","arxiv_id":"1703.04363","date":"2017-03-13","proceeding":"ICML 2017 8","authors":["Michael Gygli","Mohammad Norouzi","Anelia Angelova"],"abstract":"We approach structured output prediction by optimizing a deep value network\n(DVN) to precisely estimate the task loss on different output configurations\nfor a given input. Once the model is trained, we perform inference by gradient\ndescent on the continuous relaxations of the output variables to find outputs\nwith promising scores from the value network. When applied to image\nsegmentation, the value network takes an image and a segmentation mask as\ninputs and predicts a scalar estimating the intersection over union between the\ninput and ground truth masks. For multi-label classification, the DVN's\nobjective is to correctly predict the F1 score for any potential label\nconfiguration. The DVN framework achieves the state-of-the-art results on\nmulti-label prediction and image segmentation benchmarks.","url_abs":"http://arxiv.org/abs/1703.04363v2","url_pdf":"http://arxiv.org/pdf/1703.04363v2.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":"deep-value-networks-learn-to-evaluate-and","repo_url":"https://github.com/gyglim/dvn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"multi-label-classification-2","task_name":"MUlTI-LABEL-ClASSIFICATION"},{"task_slug":"multi-label-classification","task_name":"Multi-Label Classification"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1703.04363","atlas_url":"https://app.syntology.ai/?focus=1703.04363","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":"1703.04363"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1703.04363\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1703.04363"},"call":"get_concepts_for_paper(arxiv_id=\"1703.04363\")"}],"by_repo":[{"repo":"gyglim/dvn","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"abbd28bdc77be90845b79ba5afab8181f0ee7e5051543fed133bab3242956fc2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}