Papers › Training on Thin Air: Improve Image Classification with Generated Data

Training on Thin Air: Improve Image Classification with Generated Data

24 May 2023arXiv:2305.15316archive 2025-07-28

Yongchao Zhou, Hshmat Sahak, Jimmy Ba

Acquiring high-quality data for training discriminative models is a crucial yet challenging aspect of building effective predictive systems. In this paper, we present Diffusion Inversion, a simple yet effective method that leverages the pre-trained generative model, Stable Diffusion, to generate diverse, high-quality training data for image classification. Our approach captures the original data distribution and ensures data coverage by inverting images to the latent space of Stable Diffusion, and generates diverse novel training images by conditioning the generative model on noisy versions of these vectors. We identify three key components that allow our generated images to successfully supplant the original dataset, leading to a 2-3x enhancement in sample complexity and a 6.5x decrease in sampling time. Moreover, our approach consistently outperforms generic prompt-based steering methods and KNN retrieval baseline across a wide range of datasets. Additionally, we demonstrate the compatibility of our approach with widely-used data augmentation techniques, as well as the reliability of the generated data in supporting various neural architectures and enhancing few-shot learning.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2305.15316")

Code

Syntology Ran 4 of 9 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · honoured contract; 3 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yongchao97/diffusion_inversion officialmentioned in papermentioned on GitHubpytorchMIT 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.

Code Syntology ran Syntology

9 samples harvested; 4 ran; 1 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · honoured contract
3ran
5unverified

Licence: 0 of the 9 samples are 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 yongchao97/diffusion_inversion. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

EfficientNetB0 yongchao97/diffusion_inversion/src/models/efficientnet.py official repository ran MIT (permissive) · f7b96dbdddb56a68 · report
drop_connect yongchao97/diffusion_inversion/src/models/efficientnet.py official repository ran fingerprinted MIT (permissive) · 4304a326c593f8db · report
get_lr yongchao97/diffusion_inversion/src/train_net.py official repository ran · honoured contract MIT (permissive) · 7337f1f5ff01dcd0 · report
swish yongchao97/diffusion_inversion/src/models/efficientnet.py official repository ran fingerprinted MIT (permissive) · 8737c82de631cffc · report
center_crop yongchao97/diffusion_inversion/src/dataset.py official repository unverified MIT (permissive) · 7be19549d8b0d6dc · report
configure_dataloader yongchao97/diffusion_inversion/src/dataset.py official repository unverified MIT (permissive) · da8e9de994efee01 · report
get_full_repo_name yongchao97/diffusion_inversion/src/diffuser_inversion.py official repository unverified MIT (permissive) · d7a3942d0d5c6041 · report
np_tile_imgs yongchao97/diffusion_inversion/src/diffuser_inversion.py official repository unverified MIT (permissive) · d59f0a2fa4f321fc · report
test yongchao97/diffusion_inversion/src/train_net.py official repository unverified MIT (permissive) · 94d7f749a6ed65f8 · report

Tasks

Data AugmentationFew-Shot LearningImage ClassificationRetrievalimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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