{"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/why-relu-networks-yield-high-confidence","title":"Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem","arxiv_id":"1812.05720","date":"2018-12-13","proceeding":"CVPR 2019 6","authors":["Matthias Hein","Maksym Andriushchenko","Julian Bitterwolf"],"abstract":"Classifiers used in the wild, in particular for safety-critical systems, should not only have good generalization properties but also should know when they don't know, in particular make low confidence predictions far away from the training data. We show that ReLU type neural networks which yield a piecewise linear classifier function fail in this regard as they produce almost always high confidence predictions far away from the training data. For bounded domains like images we propose a new robust optimization technique similar to adversarial training which enforces low confidence predictions far away from the training data. We show that this technique is surprisingly effective in reducing the confidence of predictions far away from the training data while maintaining high confidence predictions and test error on the original classification task compared to standard training.","url_abs":"https://arxiv.org/abs/1812.05720v2","url_pdf":"https://arxiv.org/pdf/1812.05720v2.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":"why-relu-networks-yield-high-confidence","repo_url":"https://github.com/max-andr/relu_networks_overconfident","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1812.05720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.05720"}},"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/max-andr/relu_networks_overconfident","reach":null}],"summary":{"ran_fixture":1,"ran_violates":2,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"807e5d6763ac74c3","entry":"check_adv_robustness","repo":"max-andr/relu_networks_overconfident","repo_kind":"official","path":"analysis.py","file_url":"https://github.com/max-andr/relu_networks_overconfident/blob/HEAD/analysis.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"807e5d6763ac74c3"}},{"code_sha256_prefix":"0b0c01fbcd9fe8c4","entry":"max_conf","repo":"max-andr/relu_networks_overconfident","repo_kind":"official","path":"evaluation.py","file_url":"https://github.com/max-andr/relu_networks_overconfident/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0b0c01fbcd9fe8c4"}},{"code_sha256_prefix":"7655bfe422b9a98e","entry":"tru","repo":"max-andr/relu_networks_overconfident","repo_kind":"official","path":"evaluation.py","file_url":"https://github.com/max-andr/relu_networks_overconfident/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7655bfe422b9a98e"}},{"code_sha256_prefix":"d5890607eafaaca5","entry":"get_all_preds","repo":"max-andr/relu_networks_overconfident","repo_kind":"official","path":"evaluation.py","file_url":"https://github.com/max-andr/relu_networks_overconfident/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d5890607eafaaca5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}