{"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/explain-to-fix-a-framework-to-interpret-and","title":"Explain to Fix: A Framework to Interpret and Correct DNN Object Detector Predictions","arxiv_id":"1811.08011","date":"2018-11-19","proceeding":null,"authors":["Denis Gudovskiy","Alec Hodgkinson","Takuya Yamaguchi","Yasunori Ishii","Sotaro Tsukizawa"],"abstract":"Explaining predictions of deep neural networks (DNNs) is an important and\nnontrivial task. In this paper, we propose a practical approach to interpret\ndecisions made by a DNN object detector that has fidelity comparable to\nstate-of-the-art methods and sufficient computational efficiency to process\nlarge datasets. Our method relies on recent theory and approximates Shapley\nfeature importance values. We qualitatively and quantitatively show that the\nproposed explanation method can be used to find image features which cause\nfailures in DNN object detection. The developed software tool combined into the\n\"Explain to Fix\" (E2X) framework has a factor of 10 higher computational\nefficiency than prior methods and can be used for cluster processing using\ngraphics processing units (GPUs). Lastly, we propose a potential extension of\nthe E2X framework where the discovered missing features can be added into\ntraining dataset to overcome failures after model retraining.","url_abs":"http://arxiv.org/abs/1811.08011v1","url_pdf":"http://arxiv.org/pdf/1811.08011v1.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":"explain-to-fix-a-framework-to-interpret-and","repo_url":"https://github.com/gudovskiy/e2x","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"feature-importance","task_name":"Feature Importance"},{"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":"https://syntology.ai/paper/1811.08011","atlas_url":"https://app.syntology.ai/?focus=1811.08011","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":"1811.08011"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1811.08011\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1811.08011"},"call":"get_concepts_for_paper(arxiv_id=\"1811.08011\")"}],"by_repo":[{"repo":"gudovskiy/e2x","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":"858e0787d06b692ccee26f5dd9770083b64df925658afb7fb9217f8395d945eb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}