{"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/2311-13594","title":"Labeling Neural Representations with Inverse Recognition","arxiv_id":"2311.13594","date":"2023-11-22","proceeding":"NeurIPS 2023 11","authors":["Kirill Bykov","Laura Kopf","Shinichi Nakajima","Marius Kloft","Marina M. -C. Höhne"],"abstract":"Deep Neural Networks (DNNs) demonstrate remarkable capabilities in learning complex hierarchical data representations, but the nature of these representations remains largely unknown. Existing global explainability methods, such as Network Dissection, face limitations such as reliance on segmentation masks, lack of statistical significance testing, and high computational demands. We propose Inverse Recognition (INVERT), a scalable approach for connecting learned representations with human-understandable concepts by leveraging their capacity to discriminate between these concepts. In contrast to prior work, INVERT is capable of handling diverse types of neurons, exhibits less computational complexity, and does not rely on the availability of segmentation masks. Moreover, INVERT provides an interpretable metric assessing the alignment between the representation and its corresponding explanation and delivering a measure of statistical significance. We demonstrate the applicability of INVERT in various scenarios, including the identification of representations affected by spurious correlations, and the interpretation of the hierarchical structure of decision-making within the models.","url_abs":"https://arxiv.org/abs/2311.13594v2","url_pdf":"https://arxiv.org/pdf/2311.13594v2.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":"2311-13594","repo_url":"https://github.com/lapalap/invert","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"2311-13594","repo_url":"https://github.com/lkopf/cosy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[{"method_slug":"network-dissection","method_name":"Network Dissection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.13594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13594"}},"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/lkopf/cosy","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lapalap/invert","reach":{"status":"ok"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"12c09a1a10ca585d","entry":"collate_fn","repo":"lapalap/invert","repo_kind":"official","path":"invert/evaluation.py","file_url":"https://github.com/lapalap/invert/blob/HEAD/invert/evaluation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"12c09a1a10ca585d"}},{"code_sha256_prefix":"b6854e2a632e2f54","entry":"find_by_offset","repo":"lapalap/invert","repo_kind":"official","path":"invert/utils.py","file_url":"https://github.com/lapalap/invert/blob/HEAD/invert/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b6854e2a632e2f54"}},{"code_sha256_prefix":"0521ff1ea430c0ec","entry":"flatten_tens","repo":"lapalap/invert","repo_kind":"official","path":"invert/evaluation.py","file_url":"https://github.com/lapalap/invert/blob/HEAD/invert/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0521ff1ea430c0ec"}},{"code_sha256_prefix":"31a38a99f4731966","entry":"get_area","repo":"lapalap/invert","repo_kind":"official","path":"invert/evaluation.py","file_url":"https://github.com/lapalap/invert/blob/HEAD/invert/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"31a38a99f4731966"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}