Papers
arxiv:2103.13023

Can Vision Transformers Learn without Natural Images?

Published on Mar 24, 2021
Authors:
,
,
,
,

Abstract

A vision transformer can be pre-trained without natural images or human annotations, achieving competitive performance compared to traditional self-supervised learning methods while maintaining strong interpretability of natural image datasets.

Can we complete pre-training of Vision Transformers (ViT) without natural images and human-annotated labels? Although a pre-trained ViT seems to heavily rely on a large-scale dataset and human-annotated labels, recent large-scale datasets contain several problems in terms of privacy violations, inadequate fairness protection, and labor-intensive annotation. In the present paper, we pre-train ViT without any image collections and annotation labor. We experimentally verify that our proposed framework partially outperforms sophisticated Self-Supervised Learning (SSL) methods like SimCLRv2 and MoCov2 without using any natural images in the pre-training phase. Moreover, although the ViT pre-trained without natural images produces some different visualizations from ImageNet pre-trained ViT, it can interpret natural image datasets to a large extent. For example, the performance rates on the CIFAR-10 dataset are as follows: our proposal 97.6 vs. SimCLRv2 97.4 vs. ImageNet 98.0.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2103.13023 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2103.13023 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2103.13023 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.