{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/your-diffusion-model-is-secretly-a-zero-shot","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","arxiv_id":"2303.16203","date":"2023-03-28","proceeding":"ICCV 2023 1","authors":["Alexander C. Li","Mihir Prabhudesai","Shivam Duggal","Ellis Brown","Deepak Pathak"],"abstract":"The recent wave of large-scale text-to-image diffusion models has dramatically increased our text-based image generation abilities. These models can generate realistic images for a staggering variety of prompts and exhibit impressive compositional generalization abilities. Almost all use cases thus far have solely focused on sampling; however, diffusion models can also provide conditional density estimates, which are useful for tasks beyond image generation. In this paper, we show that the density estimates from large-scale text-to-image diffusion models like Stable Diffusion can be leveraged to perform zero-shot classification without any additional training. Our generative approach to classification, which we call Diffusion Classifier, attains strong results on a variety of benchmarks and outperforms alternative methods of extracting knowledge from diffusion models. Although a gap remains between generative and discriminative approaches on zero-shot recognition tasks, our diffusion-based approach has significantly stronger multimodal compositional reasoning ability than competing discriminative approaches. Finally, we use Diffusion Classifier to extract standard classifiers from class-conditional diffusion models trained on ImageNet. Our models achieve strong classification performance using only weak augmentations and exhibit qualitatively better \"effective robustness\" to distribution shift. Overall, our results are a step toward using generative over discriminative models for downstream tasks. Results and visualizations at https://diffusion-classifier.github.io/","url_abs":"https://arxiv.org/abs/2303.16203v3","url_pdf":"https://arxiv.org/pdf/2303.16203v3.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":"your-diffusion-model-is-secretly-a-zero-shot","repo_url":"https://github.com/diffusion-classifier/diffusion-classifier","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"your-diffusion-model-is-secretly-a-zero-shot","repo_url":"https://github.com/LiYinqi/DIVE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"your-diffusion-model-is-secretly-a-zero-shot","repo_url":"https://github.com/SamsungSAILMontreal/ForestDiffusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"your-diffusion-model-is-secretly-a-zero-shot","repo_url":"https://github.com/tajamul21/fate","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"relational-reasoning","task_name":"Relational Reasoning"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":"zero-shot-transfer-image-classification","task_name":"Zero-Shot Transfer Image Classification"},{"task_slug":null,"task_name":"zero-shot-classification"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-imagenet-a","task":"Domain Generalization","dataset":"ImageNet-A","model":"Diffusion Classifier","rank_in_archive_order":27,"of":39,"metrics":{"Top-1 accuracy %":"30.2"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-fgvc","task":"Fine-Grained Image Classification","dataset":"FGVC Aircraft","model":"Diffusion Classifier (zero-shot)","rank_in_archive_order":55,"of":57,"metrics":{"Accuracy":"26.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"Diffusion Classifier (zero-shot)","rank_in_archive_order":217,"of":265,"metrics":{"Percentage correct":"88.5"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-flowers-102","task":"Image Classification","dataset":"Flowers-102","model":"Diffusion Classifier (zero-shot)","rank_in_archive_order":51,"of":52,"metrics":{"Per-Class Accuracy":"66.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"Diffusion Classifier","rank_in_archive_order":779,"of":1060,"metrics":{"Top 1 Accuracy":"79.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-objectnet-imagenet","task":"Image Classification","dataset":"ObjectNet (ImageNet classes)","model":"Diffusion Classifier (zero-shot)","rank_in_archive_order":1,"of":2,"metrics":{"Top 1 Accuracy":"43.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-objectnet-imagenet","task":"Image Classification","dataset":"ObjectNet (ImageNet classes)","model":"Diffusion Classifier","rank_in_archive_order":2,"of":2,"metrics":{"Top 1 Accuracy":"33.9"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-oxford-iiit-pets-1","task":"Image Classification","dataset":"Oxford-IIIT Pets","model":"Diffusion Classifier (zero-shot)","rank_in_archive_order":6,"of":6,"metrics":{"Per-Class Accuracy":"87.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"Diffusion Classifier (zero-shot)","rank_in_archive_order":18,"of":117,"metrics":{"Percentage correct":"95.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-winoground","task":"Visual Reasoning","dataset":"Winoground","model":"Diffusion Classifier (zero-shot)","rank_in_archive_order":56,"of":114,"metrics":{"Text Score":"34.00"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-17","task":"Zero-Shot Transfer Image Classification","dataset":"Food-101","model":"Diffusion Classifier (zero-shot)","rank_in_archive_order":5,"of":5,"metrics":{"Top 1 Accuracy":"77.7"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-1","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet","model":"Diffusion Classifier (zero-shot)","rank_in_archive_order":20,"of":23,"metrics":{"Accuracy (Private)":"61.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.16203","atlas_url":"https://app.syntology.ai/?focus=2303.16203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16203"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2303.16203"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2303.16203"},"call":"get_harvested_code_for_paper(arxiv_id=\"2303.16203\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2303.16203"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2303.16203\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2303.16203"},"call":"get_concepts_for_paper(arxiv_id=\"2303.16203\")"}],"by_repo":[{"repo":"diffusion-classifier/diffusion-classifier","kind":"official","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"LiYinqi/DIVE","kind":"listed","samples":1,"ran":1,"instrument":1,"unverified":0},{"repo":"SamsungSAILMontreal/ForestDiffusion","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2309.16779"],"harvested_for_calls":[{"arxiv_id":"2309.16779","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2309.16779"},"call":"get_harvested_code_for_paper(arxiv_id=\"2309.16779\")"}]},{"repo":"tajamul21/fate","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2303.16203.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2303.16203.svg"},"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"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/diffusion-classifier/diffusion-classifier","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tajamul21/fate","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LiYinqi/DIVE","reach":null}],"summary":{"ran_honours":1,"ran_fixture":1},"n_samples":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":1,"ran":1,"n_ran_checked":1,"n_instrument":0,"repositories":1},"listed":{"samples":1,"ran":1,"n_ran_checked":0,"n_instrument":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":1,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":2,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-22","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"5236fd023ace5c38","code_sha256_prefix":"5236fd023ace5c38","entry":"mean_per_class_acc","repo":"diffusion-classifier/diffusion-classifier","repo_kind":"official","path":"scripts/print_acc.py","file_url":"https://github.com/diffusion-classifier/diffusion-classifier/blob/HEAD/scripts/print_acc.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"correct:Tensor/1/float, labels:Tensor/1/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"5236fd023ace5c38"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, diffusion-classifier/diffusion-classifier when it was checked","mcp_get_code":{"code_sha256":"5236fd023ace5c38"}},{"code_sha256":"9fbea808db47dc66","code_sha256_prefix":"9fbea808db47dc66","entry":"project_logits","repo":"LiYinqi/DIVE","repo_kind":"listed","path":"Classification/diffusion/dataset/imagenet.py","file_url":"https://github.com/LiYinqi/DIVE/blob/HEAD/Classification/diffusion/dataset/imagenet.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"logits:Tensor/2/float, class_sublist_mask:Tensor/1/bool, device:device/0/?","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/project-logits","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9fbea808db47dc66"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"9f25105419cee629645d092df0b69957d43b8c6f0f7c4143f2bcb3ad6f80fc85","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}