{"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/how-to-probe-simple-yet-effective-techniques","title":"How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations","arxiv_id":"2503.00641","date":"2025-03-01","proceeding":null,"authors":["Siddhartha Gairola","Moritz Böhle","Francesco Locatello","Bernt Schiele"],"abstract":"Post-hoc importance attribution methods are a popular tool for \"explaining\" Deep Neural Networks (DNNs) and are inherently based on the assumption that the explanations can be applied independently of how the models were trained. Contrarily, in this work we bring forward empirical evidence that challenges this very notion. Surprisingly, we discover a strong dependency on and demonstrate that the training details of a pre-trained model's classification layer (less than 10 percent of model parameters) play a crucial role, much more than the pre-training scheme itself. This is of high practical relevance: (1) as techniques for pre-training models are becoming increasingly diverse, understanding the interplay between these techniques and attribution methods is critical; (2) it sheds light on an important yet overlooked assumption of post-hoc attribution methods which can drastically impact model explanations and how they are interpreted eventually. With this finding we also present simple yet effective adjustments to the classification layers, that can significantly enhance the quality of model explanations. We validate our findings across several visual pre-training frameworks (fully-supervised, self-supervised, contrastive vision-language training) and analyse how they impact explanations for a wide range of attribution methods on a diverse set of evaluation metrics.","url_abs":"https://arxiv.org/abs/2503.00641v1","url_pdf":"https://arxiv.org/pdf/2503.00641v1.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":"how-to-probe-simple-yet-effective-techniques","repo_url":"https://github.com/sidgairo18/how-to-probe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.00641","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.00641"}},"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":"deterministic:regex_extraction","url":"https://github.com/sidgairo18/how-to-probe","reach":null}],"summary":{"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"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":"35d2da52cdbf9e9c","entry":"binaryMaskIOU","repo":"sidgairo18/how-to-probe","repo_kind":"official","path":"evaluate_attributions/epg/eval_coco_epg.py","file_url":"https://github.com/sidgairo18/how-to-probe/blob/HEAD/evaluate_attributions/epg/eval_coco_epg.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"35d2da52cdbf9e9c"}},{"code_sha256_prefix":"608bd342a2b996d8","entry":"get_att_maps","repo":"sidgairo18/how-to-probe","repo_kind":"official","path":"evaluate_attributions/epg/eval_coco_epg.py","file_url":"https://github.com/sidgairo18/how-to-probe/blob/HEAD/evaluate_attributions/epg/eval_coco_epg.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":"608bd342a2b996d8"}},{"code_sha256_prefix":"7e3e2ada8ffc779c","entry":"get_att_maps","repo":"sidgairo18/how-to-probe","repo_kind":"official","path":"evaluate_attributions/gridpg/eval_gridpg_compactness_complexity.py","file_url":"https://github.com/sidgairo18/how-to-probe/blob/HEAD/evaluate_attributions/gridpg/eval_gridpg_compactness_complexity.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":"7e3e2ada8ffc779c"}},{"code_sha256_prefix":"8882b65cff5414ae","entry":"get_bcos_attributions","repo":"sidgairo18/how-to-probe","repo_kind":"official","path":"evaluate_attributions/epg/eval_coco_epg.py","file_url":"https://github.com/sidgairo18/how-to-probe/blob/HEAD/evaluate_attributions/epg/eval_coco_epg.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":"8882b65cff5414ae"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}