Papers › Your Diffusion Model is Secretly a Zero-Shot Classifier

Your Diffusion Model is Secretly a Zero-Shot Classifier

28 Mar 2023ICCV 2023 1arXiv:2303.16203archive 2025-07-28

Alexander C. Li, Mihir Prabhudesai, Shivam Duggal, Ellis Brown, Deepak Pathak

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/

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 2 code samples harvested from 2 repositories linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

diffusion-classifier/diffusion-classifier officialmentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
LiYinqi/DIVE mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
SamsungSAILMontreal/ForestDiffusion mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Intriguing properties of generative classifiers (arXiv:2309.16779; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
tajamul21/fate mentioned on GitHubtfnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

2 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran; the contract check could not run

Licence: 1 of the 2 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives 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” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

diffusion-classifier/diffusion-classifier official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
mean_per_class_acc scripts/print_acc.py ran · honoured contract fingerprinted no licence file found · pointer only · 5236fd023ace5c38 · report fixture: signature correct:Tensor/1/float, labels:Tensor/1/int · returned Tensor · level recorded 2026-09-22
LiYinqi/DIVE community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
project_logits in 9 papers Classification/diffusion/dataset/imagenet.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 9fbea808db47dc66 · report fixture: signature logits:Tensor/2/float, class_sublist_mask:Tensor/1/bool, device:device/0/? · returned Tensor · level recorded 2026-09-22

Tasks

Domain GeneralizationFine-Grained Image ClassificationImage ClassificationImage GenerationRelational ReasoningVisual ReasoningZero-Shot LearningZero-Shot Transfer Image Classification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization ImageNet-A Diffusion Classifier Top-1 accuracy % 30.2 #27 of 39 Archive leaderboard report
Fine-Grained Image Classification FGVC Aircraft Diffusion Classifier (zero-shot) Accuracy 26.4 #55 of 57 Archive leaderboard report
Image Classification CIFAR-10 Diffusion Classifier (zero-shot) Percentage correct 88.5 #217 of 265 Archive leaderboard report
Image Classification Flowers-102 Diffusion Classifier (zero-shot) Per-Class Accuracy 66.3 #51 of 52 Archive leaderboard report
Image Classification ImageNet Diffusion Classifier Top 1 Accuracy 79.1% #779 of 1060 Archive leaderboard report
Image Classification ObjectNet (ImageNet classes) Diffusion Classifier (zero-shot) Top 1 Accuracy 43.4 #1 of 2 Archive leaderboard report
Image Classification ObjectNet (ImageNet classes) Diffusion Classifier Top 1 Accuracy 33.9 #2 of 2 Archive leaderboard report
Image Classification Oxford-IIIT Pets Diffusion Classifier (zero-shot) Per-Class Accuracy 87.3 #6 of 6 Archive leaderboard report
Image Classification STL-10 Diffusion Classifier (zero-shot) Percentage correct 95.4 #18 of 117 Archive leaderboard report
Visual Reasoning Winoground Diffusion Classifier (zero-shot) Text Score 34.00 #56 of 114 Archive leaderboard report
Zero-Shot Transfer Image Classification Food-101 Diffusion Classifier (zero-shot) Top 1 Accuracy 77.7 #5 of 5 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet Diffusion Classifier (zero-shot) Accuracy (Private) 61.4 #20 of 23 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections