{"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/intriguing-properties-of-generative","title":"Intriguing properties of generative classifiers","arxiv_id":"2309.16779","date":"2023-09-28","proceeding":null,"authors":["Priyank Jaini","Kevin Clark","Robert Geirhos"],"abstract":"What is the best paradigm to recognize objects -- discriminative inference (fast but potentially prone to shortcut learning) or using a generative model (slow but potentially more robust)? We build on recent advances in generative modeling that turn text-to-image models into classifiers. This allows us to study their behavior and to compare them against discriminative models and human psychophysical data. We report four intriguing emergent properties of generative classifiers: they show a record-breaking human-like shape bias (99% for Imagen), near human-level out-of-distribution accuracy, state-of-the-art alignment with human classification errors, and they understand certain perceptual illusions. Our results indicate that while the current dominant paradigm for modeling human object recognition is discriminative inference, zero-shot generative models approximate human object recognition data surprisingly well.","url_abs":"https://arxiv.org/abs/2309.16779v2","url_pdf":"https://arxiv.org/pdf/2309.16779v2.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":"intriguing-properties-of-generative","repo_url":"https://github.com/SamsungSAILMontreal/ForestDiffusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-recognition-on-shape-bias","task":"Object Recognition","dataset":"shape bias","model":"Imagen","rank_in_archive_order":1,"of":18,"metrics":{"shape bias":"98.7"},"uses_additional_data":false},{"leaderboard":"/sota/object-recognition-on-shape-bias","task":"Object Recognition","dataset":"shape bias","model":"Stable Diffusion","rank_in_archive_order":2,"of":18,"metrics":{"shape bias":"92.7"},"uses_additional_data":false},{"leaderboard":"/sota/object-recognition-on-shape-bias","task":"Object Recognition","dataset":"shape bias","model":"Parti","rank_in_archive_order":3,"of":18,"metrics":{"shape bias":"91.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.16779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16779"}},"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/SamsungSAILMontreal/ForestDiffusion","reach":{"status":"ok"}}],"summary":{"ran":8,"ran_draft_wrong":1,"ran_violates":1,"unverified":2},"by_repo_kind":{"listed":{"samples":12,"ran":10,"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":12,"samples":[{"code_sha256_prefix":"e66a901d3f6cb388","entry":"converged","repo":"SamsungSAILMontreal/ForestDiffusion","repo_kind":"listed","path":"softimpute.py","file_url":"https://github.com/SamsungSAILMontreal/ForestDiffusion/blob/HEAD/softimpute.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":"e66a901d3f6cb388"}},{"code_sha256_prefix":"e311e63553012e76","entry":"get_optimizer","repo":"SamsungSAILMontreal/ForestDiffusion","repo_kind":"listed","path":"STaSy/losses.py","file_url":"https://github.com/SamsungSAILMontreal/ForestDiffusion/blob/HEAD/STaSy/losses.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":"e311e63553012e76"}},{"code_sha256_prefix":"bbbb6c22bd6a9a4a","entry":"nanmean","repo":"SamsungSAILMontreal/ForestDiffusion","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/SamsungSAILMontreal/ForestDiffusion/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bbbb6c22bd6a9a4a"}},{"code_sha256_prefix":"82b1e0d73f4df6cd","entry":"normalization","repo":"SamsungSAILMontreal/ForestDiffusion","repo_kind":"listed","path":"gain.py","file_url":"https://github.com/SamsungSAILMontreal/ForestDiffusion/blob/HEAD/gain.py","link_basis":"plan_row","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":"82b1e0d73f4df6cd"}},{"code_sha256_prefix":"18269deb82a2a3f6","entry":"optimization_manager","repo":"SamsungSAILMontreal/ForestDiffusion","repo_kind":"listed","path":"STaSy/losses.py","file_url":"https://github.com/SamsungSAILMontreal/ForestDiffusion/blob/HEAD/STaSy/losses.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":"18269deb82a2a3f6"}},{"code_sha256_prefix":"127379550e5e9139","entry":"pick_epsilon","repo":"SamsungSAILMontreal/ForestDiffusion","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/SamsungSAILMontreal/ForestDiffusion/blob/HEAD/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":"127379550e5e9139"}},{"code_sha256_prefix":"f4957252157d03ef","entry":"renormalization","repo":"SamsungSAILMontreal/ForestDiffusion","repo_kind":"listed","path":"gain.py","file_url":"https://github.com/SamsungSAILMontreal/ForestDiffusion/blob/HEAD/gain.py","link_basis":"plan_row","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":"f4957252157d03ef"}},{"code_sha256_prefix":"81dbfd5afe49f6a9","entry":"softimpute","repo":"SamsungSAILMontreal/ForestDiffusion","repo_kind":"listed","path":"softimpute.py","file_url":"https://github.com/SamsungSAILMontreal/ForestDiffusion/blob/HEAD/softimpute.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":"81dbfd5afe49f6a9"}},{"code_sha256_prefix":"7c508037b40522af","entry":"str2bool","repo":"SamsungSAILMontreal/ForestDiffusion","repo_kind":"listed","path":"script_generation.py","file_url":"https://github.com/SamsungSAILMontreal/ForestDiffusion/blob/HEAD/script_generation.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7c508037b40522af"}},{"code_sha256_prefix":"bec9ca3c9ff3e822","entry":"test_x","repo":"SamsungSAILMontreal/ForestDiffusion","repo_kind":"listed","path":"softimpute.py","file_url":"https://github.com/SamsungSAILMontreal/ForestDiffusion/blob/HEAD/softimpute.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":"bec9ca3c9ff3e822"}},{"code_sha256_prefix":"c3b530881a1f5071","entry":"gain","repo":"SamsungSAILMontreal/ForestDiffusion","repo_kind":"listed","path":"gain.py","file_url":"https://github.com/SamsungSAILMontreal/ForestDiffusion/blob/HEAD/gain.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":"c3b530881a1f5071"}},{"code_sha256_prefix":"4db664a683098ffe","entry":"quantile","repo":"SamsungSAILMontreal/ForestDiffusion","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/SamsungSAILMontreal/ForestDiffusion/blob/HEAD/utils.py","link_basis":"harvester_set","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":"4db664a683098ffe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}