In-Person Poster presentation / poster accept

The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image

Yuki Asano · Aaqib Saeed

MH1-2-3-4 #82

Keywords: [ Deep Learning and representational learning ] [ distillation ] [ Single Image Learning ] [ Augmentations ]

[ Abstract ]
[ OpenReview
Wed 3 May 2:30 a.m. PDT — 4:30 a.m. PDT

Abstract: 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 $256^{3\cdot224\cdot224}$ 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.

Chat is not available.