What can neural networks learn about the visual world when provided with only a single image as input? While any image obviously cannot contain the multitudes of all existing objects, scenes and lighting conditions - within the space of all 256^(3x224x224) possible 224-sized square images, it might still provide a strong prior for natural images. To analyze this `augmented image prior' hypothesis, we develop a simple framework for training neural networks from scratch using a single image and augmentations using knowledge distillation from a supervised pretrained teacher. With this, we find the answer to the above question to be: `surprisingly, a lot'. In quantitative terms, we find accuracies of 94%/74% on CIFAR-10/100, 69% on ImageNet, and by extending this method to video and audio, 51% on Kinetics-400 and 84% on SpeechCommands. In extensive analyses spanning 13 datasets, we disentangle the effect of augmentations, choice of data and network architectures and also provide qualitative evaluations that include lucid `panda neurons' in networks that have never even seen one.
@article{arxiv.2112.00725,
title = {The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image},
author = {Yuki M. Asano and Aaqib Saeed},
journal= {arXiv preprint arXiv:2112.00725},
year = {2023}
}
Comments
Accepted at ICLR'23. Webpage: https://single-image-distill.github.io/, code: https://github.com/yukimasano/single-img-extrapolating