Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers

• URL: http://arxiv.org/abs/2511.13945v1
• Date: Mon, 17 Nov 2025 22:00:59 GMT
• Title: Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers
• Authors: Zachary Shinnick, Liangze Jiang, Hemanth Saratchandran, Damien Teney, Anton van den Hengel,
• Abstract summary: We generate data with simple algorithms such as formal grammars, so the results bear no relationship to either natural or synthetic images.<n>We use this procedurally-generated data to pretrain ViTs in a warm-up phase that bypasses their visual patch embedding mechanisms.<n>When followed by standard image-based training, this warm-up significantly improves data efficiency, convergence speed, and downstream performance.
• Score: 40.183555811204506
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformers show remarkable versatility across domains, suggesting the existence of inductive biases beneficial across modalities. In this work, we explore a new way to instil such generic biases in vision transformers (ViTs) by pretraining on procedurally-generated data devoid of visual or semantic content. We generate this data with simple algorithms such as formal grammars, so the results bear no relationship to either natural or synthetic images. We use this procedurally-generated data to pretrain ViTs in a warm-up phase that bypasses their visual patch embedding mechanisms, thus encouraging the models to internalise abstract computational priors. When followed by standard image-based training, this warm-up significantly improves data efficiency, convergence speed, and downstream performance. On ImageNet-1k for example, allocating just 1% of the training budget to procedural data improves final accuracy by over 1.7%. In terms of its effect on performance, 1% procedurally generated data is thus equivalent to 28% of the ImageNet-1k data. These findings suggest a promising path toward new data-efficient and domain-agnostic pretraining strategies.

Related papers

• Visual Fourier Prompt Tuning [63.66866445034855]
  We propose the Visual Fourier Prompt Tuning (VFPT) method as a general and effective solution for adapting large-scale transformer-based models. Our approach incorporates the Fast Fourier Transform into prompt embeddings and harmoniously considers both spatial and frequency domain information. Our results demonstrate that our approach outperforms current state-of-the-art baselines on two benchmarks.
  arXiv  Detail & Related papers  (2024-11-02T18:18:35Z)
• Scaling Backwards: Minimal Synthetic Pre-training? [52.78699562832907]
  We show that pre-training is effective even with minimal synthetic images. We find that a substantial reduction of synthetic images from 1k to 1 can even lead to an increase in pre-training performance. We extend our method from synthetic images to real images to see if a single real image can show similar pre-training effect.
  arXiv  Detail & Related papers  (2024-08-01T16:20:02Z)
• Curriculum Dataset Distillation [33.167484258219766]
  We present a curriculum-based dataset distillation framework aiming to harmonize performance and scalability.<n>This framework strategically distills synthetic images, adhering to a curriculum that transitions from simple to complex.<n>Our framework sets new benchmarks in large-scale dataset distillation, achieving substantial improvements of 11.1% on Tiny-ImageNet, 9.0% on ImageNet-1K, and 7.3% on ImageNet-21K.
  arXiv  Detail & Related papers  (2024-05-15T07:27:14Z)
• PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining [13.823621924706348]
  Differential Privacy (DP) image data synthesis allows organizations to share and utilize synthetic images without privacy concerns. Previous methods incorporate the advanced techniques of generative models and pre-training on a public dataset to produce exceptional DP image data. This paper proposes a novel DP image synthesis method, termed PRIVIMAGE, which meticulously selects pre-training data.
  arXiv  Detail & Related papers  (2023-10-19T14:04:53Z)
• NaturalInversion: Data-Free Image Synthesis Improving Real-World Consistency [1.1470070927586016]
  We introduce NaturalInversion, a novel model inversion-based method to synthesize images that agrees well with the original data distribution without using real data. We show that our images are more consistent with original data distribution than prior works by visualization and additional analysis.
  arXiv  Detail & Related papers  (2023-06-29T03:43:29Z)
• T-ADAF: Adaptive Data Augmentation Framework for Image Classification Network based on Tensor T-product Operator [0.0]
  This paper proposes an Adaptive Data Augmentation Framework based on the tensor T-product Operator. It triples one image data to be trained and gain the result from all these three images together with only less than 0.1% increase in the number of parameters. Numerical experiments show that our data augmentation framework can improve the performance of original neural network model by 2%.
  arXiv  Detail & Related papers  (2023-06-07T08:30:44Z)
• Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves [18.5408134000081]
  Formula-driven supervised learning has been shown to be an effective method for pre-training transformers. VisualAtom-21k is used for pre-training ViT-Base, the top-1 accuracy reached 83.7% when fine-tuning on ImageNet-1k. Unlike JFT-300M which is a static dataset, the quality of synthetic datasets will continue to improve.
  arXiv  Detail & Related papers  (2023-03-02T09:47:28Z)
• Skip-Attention: Improving Vision Transformers by Paying Less Attention [55.47058516775423]
  Vision computation transformers (ViTs) use expensive self-attention operations in every layer. We propose SkipAt, a method to reuse self-attention from preceding layers to approximate attention at one or more subsequent layers. We show the effectiveness of our method in image classification and self-supervised learning on ImageNet-1K, semantic segmentation on ADE20K, image denoising on SIDD, and video denoising on DAVIS.
  arXiv  Detail & Related papers  (2023-01-05T18:59:52Z)
• GradViT: Gradient Inversion of Vision Transformers [83.54779732309653]
  We demonstrate the vulnerability of vision transformers (ViTs) to gradient-based inversion attacks. We introduce a method, named GradViT, that optimize random noise into naturally looking images. We observe unprecedentedly high fidelity and closeness to the original (hidden) data.
  arXiv  Detail & Related papers  (2022-03-22T17:06:07Z)
• When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations [111.44860506703307]
  Vision Transformers (ViTs) and existing VisionNets signal efforts on replacing hand-wired features or inductive throughputs with general-purpose neural architectures. This paper investigates ViTs and Res-Mixers from the lens of loss geometry, intending to improve the models' data efficiency at training and inference. We show that the improved robustness attributes to sparser active neurons in the first few layers. The resultant ViTs outperform Nets of similar size and smoothness when trained from scratch on ImageNet without large-scale pretraining or strong data augmentations.
  arXiv  Detail & Related papers  (2021-06-03T02:08:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.