{"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/building-reliable-explanations-of-unreliable","title":"Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation","arxiv_id":"2103.14332","date":"2021-03-26","proceeding":"CVPR 2021 1","authors":["Dohun Lim","HyeonSeok Lee","Sungchan Kim"],"abstract":"We present a novel method for reliably explaining the predictions of neural networks. We consider an explanation reliable if it identifies input features relevant to the model output by considering the input and the neighboring data points. Our method is built on top of the assumption of smooth landscape in a loss function of the model prediction: locally consistent loss and gradient profile. A theoretical analysis established in this study suggests that those locally smooth model explanations are learned using a batch of noisy copies of the input with the L1 regularization for a saliency map. Extensive experiments support the analysis results, revealing that the proposed saliency maps retrieve the original classes of adversarial examples crafted against both naturally and adversarially trained models, significantly outperforming previous methods. We further demonstrated that such good performance results from the learning capability of this method to identify input features that are truly relevant to the model output of the input and the neighboring data points, fulfilling the requirements of a reliable explanation.","url_abs":"https://arxiv.org/abs/2103.14332v2","url_pdf":"https://arxiv.org/pdf/2103.14332v2.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":"building-reliable-explanations-of-unreliable","repo_url":"https://github.com/JBNU-VL/RelEx","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"l1-regularization","method_name":"L1 Regularization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.14332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.14332"}},"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/JBNU-VL/RelEx","reach":null}],"summary":{"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":"52efb72452226ea7","entry":"RelEx","repo":"JBNU-VL/RelEx","repo_kind":"official","path":"models/saliency/optim_methods/relex.py","file_url":"https://github.com/JBNU-VL/RelEx/blob/HEAD/models/saliency/optim_methods/relex.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"52efb72452226ea7"}},{"code_sha256_prefix":"73b2b4d12392b434","entry":"Loss","repo":"JBNU-VL/RelEx","repo_kind":"official","path":"models/saliency/optim_methods/relex.py","file_url":"https://github.com/JBNU-VL/RelEx/blob/HEAD/models/saliency/optim_methods/relex.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":"73b2b4d12392b434"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}