{"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/right-for-the-right-concept-revising-neuro","title":"Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations","arxiv_id":"2011.12854","date":"2020-11-25","proceeding":"CVPR 2021 1","authors":["Wolfgang Stammer","Patrick Schramowski","Kristian Kersting"],"abstract":"Most explanation methods in deep learning map importance estimates for a model's prediction back to the original input space. These \"visual\" explanations are often insufficient, as the model's actual concept remains elusive. Moreover, without insights into the model's semantic concept, it is difficult -- if not impossible -- to intervene on the model's behavior via its explanations, called Explanatory Interactive Learning. Consequently, we propose to intervene on a Neuro-Symbolic scene representation, which allows one to revise the model on the semantic level, e.g. \"never focus on the color to make your decision\". We compiled a novel confounded visual scene data set, the CLEVR-Hans data set, capturing complex compositions of different objects. The results of our experiments on CLEVR-Hans demonstrate that our semantic explanations, i.e. compositional explanations at a per-object level, can identify confounders that are not identifiable using \"visual\" explanations only. More importantly, feedback on this semantic level makes it possible to revise the model from focusing on these factors.","url_abs":"https://arxiv.org/abs/2011.12854v6","url_pdf":"https://arxiv.org/pdf/2011.12854v6.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":"right-for-the-right-concept-revising-neuro","repo_url":"https://github.com/ml-research/CLEVR-Hans","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"right-for-the-right-concept-revising-neuro","repo_url":"https://github.com/ml-research/NeSyXIL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"right-for-the-right-concept-revising-neuro","repo_url":"https://github.com/ml-research/NeSyConceptLearner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"clevr-hans","name":"CLEVR-Hans","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.12854","atlas_url":"https://app.syntology.ai/?focus=2011.12854","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12854"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ml-research/CLEVR-Hans","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ml-research/NeSyXIL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ml-research/NeSyConceptLearner","reach":{"status":"unanswered"}}],"summary":{"ran_fixture":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":0,"samples":[{"code_sha256_prefix":"902801a457ed91db","entry":"run_test_final","repo":"ml-research/NeSyXIL","repo_kind":"official","path":"src/clevr_hans/cnn/train_resnet34_xil.py","file_url":"https://github.com/ml-research/NeSyXIL/blob/HEAD/src/clevr_hans/cnn/train_resnet34_xil.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"902801a457ed91db"}},{"code_sha256_prefix":"13614f949779b0bc","entry":"run_test_final","repo":"ml-research/NeSyXIL","repo_kind":"official","path":"src/clevr_hans/nesy_xil/train_clevr_hans_concept_learner_xil.py","file_url":"https://github.com/ml-research/NeSyXIL/blob/HEAD/src/clevr_hans/nesy_xil/train_clevr_hans_concept_learner_xil.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"13614f949779b0bc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}