{"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-neural-networks-can-be-improved-using","title":"Deep neural networks can be improved using human-derived contextual expectations","arxiv_id":"1611.07218","date":"2016-11-22","proceeding":null,"authors":["Harish Katti","Marius V. Peelen","S. P. Arun"],"abstract":"Real-world objects occur in specific contexts. Such context has been shown to\nfacilitate detection by constraining the locations to search. But can context\ndirectly benefit object detection? To do so, context needs to be learned\nindependently from target features. This is impossible in traditional object\ndetection where classifiers are trained on images containing both target\nfeatures and surrounding context. In contrast, humans can learn context and\ntarget features separately, such as when we see highways without cars. Here we\nshow for the first time that human-derived scene expectations can be used to\nimprove object detection performance in machines. To measure contextual\nexpectations, we asked human subjects to indicate the scale, location and\nlikelihood at which cars or people might occur in scenes without these objects.\nHumans showed highly systematic expectations that we could accurately predict\nusing scene features. This allowed us to predict human expectations on novel\nscenes without requiring manual annotation. On augmenting deep neural networks\nwith predicted human expectations, we obtained substantial gains in accuracy\nfor detecting cars and people (1-3%) as well as on detecting associated objects\n(3-20%). In contrast, augmenting deep networks with other conventional features\nyielded far smaller gains. This improvement was due to relatively poor matches\nat highly likely locations being correctly labelled as target and conversely\nstrong matches at unlikely locations being correctly rejected as false alarms.\nTaken together, our results show that augmenting deep neural networks with\nhuman-derived context features improves their performance, suggesting that\nhumans learn scene context separately unlike deep networks.","url_abs":"http://arxiv.org/abs/1611.07218v4","url_pdf":"http://arxiv.org/pdf/1611.07218v4.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-neural-networks-can-be-improved-using","repo_url":"https://github.com/harish2006/cntxt_likelihood","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"harish2006/cntxt_likelihood","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":"a98081f01ed34316fcac86b3b7ce300af998468bcb83e9ef07cd62c0e9f456fd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}