{"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/reducing-network-agnostophobia","title":"Reducing Network Agnostophobia","arxiv_id":"1811.04110","date":"2018-11-09","proceeding":"NeurIPS 2018 12","authors":["Akshay Raj Dhamija","Manuel Günther","Terrance E. Boult"],"abstract":"Agnostophobia, the fear of the unknown, can be experienced by deep learning\nengineers while applying their networks to real-world applications.\nUnfortunately, network behavior is not well defined for inputs far from a\nnetworks training set. In an uncontrolled environment, networks face many\ninstances that are not of interest to them and have to be rejected in order to\navoid a false positive. This problem has previously been tackled by researchers\nby either a) thresholding softmax, which by construction cannot return \"none of\nthe known classes\", or b) using an additional background or garbage class. In\nthis paper, we show that both of these approaches help, but are generally\ninsufficient when previously unseen classes are encountered. We also introduce\na new evaluation metric that focuses on comparing the performance of multiple\napproaches in scenarios where such unseen classes or unknowns are encountered.\nOur major contributions are simple yet effective Entropic Open-Set and\nObjectosphere losses that train networks using negative samples from some\nclasses. These novel losses are designed to maximize entropy for unknown inputs\nwhile increasing separation in deep feature space by modifying magnitudes of\nknown and unknown samples. Experiments on networks trained to classify classes\nfrom MNIST and CIFAR-10 show that our novel loss functions are significantly\nbetter at dealing with unknown inputs from datasets such as Devanagari,\nNotMNIST, CIFAR-100, and SVHN.","url_abs":"http://arxiv.org/abs/1811.04110v2","url_pdf":"http://arxiv.org/pdf/1811.04110v2.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":"reducing-network-agnostophobia","repo_url":"https://github.com/Vastlab/Reducing-Network-Agnostophobia","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"reducing-network-agnostophobia","repo_url":"https://github.com/Andrewwango/open-set-classif","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"reducing-network-agnostophobia","repo_url":"https://github.com/Andrewwango/open-set-resnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"reducing-network-agnostophobia","repo_url":"https://github.com/ROBOTICSENGINEER/Reducing-Network-Agnostophobia-Center-Loss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.04110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.04110"}},"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/ROBOTICSENGINEER/Reducing-Network-Agnostophobia-Center-Loss","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Vastlab/Reducing-Network-Agnostophobia","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Andrewwango/open-set-resnet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Andrewwango/open-set-classif","reach":{"status":"ok"}}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"ran":0,"repositories":1}},"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":"f3f069af6fdc33f7","entry":"read_images","repo":"ROBOTICSENGINEER/Reducing-Network-Agnostophobia-Center-Loss","repo_kind":"listed","path":"MNIST/data_prep.py","file_url":"https://github.com/ROBOTICSENGINEER/Reducing-Network-Agnostophobia-Center-Loss/blob/HEAD/MNIST/data_prep.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f3f069af6fdc33f7"}},{"code_sha256_prefix":"b25733043a18945d","entry":"read_labels","repo":"ROBOTICSENGINEER/Reducing-Network-Agnostophobia-Center-Loss","repo_kind":"listed","path":"MNIST/data_prep.py","file_url":"https://github.com/ROBOTICSENGINEER/Reducing-Network-Agnostophobia-Center-Loss/blob/HEAD/MNIST/data_prep.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b25733043a18945d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}