# Procedural Image Programs for Representation Learning

Source: [Procedural Image Programs for Representation Learning](<https://www.sota2.com/research/paper/68fa71251e209131cea4f787>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:59:40.801Z

Authors: Manel Baradad, Chun-Fu Chen, Jonas Wulff, Tongzhou Wang, Rogerio Feris, Antonio Torralba, Phillip Isola

Published: 2022-11-29T17:34:22.000Z

## Abstract

Learning image representations using synthetic data allows training neural networks without some of the concerns associated with real images, such as privacy and bias. Existing work focuses on a handful of curated generative processes which require expert knowledge to design, making it hard to scale up. To overcome this, we propose training with a large dataset of twenty-one thousand programs, each one generating a diverse set of synthetic images. These programs are short code snippets, which are easy to modify and fast to execute using OpenGL. The proposed dataset can be used for both supervised and unsupervised representation learning, and reduces the gap between pre-training with real and procedurally generated images by 38%.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Retrieval on ImageNet-100 (val)](<https://www.sota2.com/research/sota/image-retrieval-on-imagenet-100-val.md>): Image Retrieval; ImageNet-100 (val); Top-1 Accuracy: 43.24.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2211.16412>)

[PDF](<https://arxiv.org/pdf/2211.16412.pdf>)