How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers

06/18/2021
by   Andreas Steiner, et al.
0

Vision Transformers (ViT) have been shown to attain highly competitive performance for a wide range of vision applications, such as image classification, object detection and semantic image segmentation. In comparison to convolutional neural networks, the Vision Transformer's weaker inductive bias is generally found to cause an increased reliance on model regularization or data augmentation (“AugReg” for short) when training on smaller training datasets. We conduct a systematic empirical study in order to better understand the interplay between the amount of training data, AugReg, model size and compute budget. As one result of this study we find that the combination of increased compute and AugReg can yield models with the same performance as models trained on an order of magnitude more training data: we train ViT models of various sizes on the public ImageNet-21k dataset which either match or outperform their counterparts trained on the larger, but not publicly available JFT-300M dataset.

READ FULL TEXT
research
12/16/2021

How to augment your ViTs? Consistency loss and StyleAug, a random style transfer augmentation

The Vision Transformer (ViT) architecture has recently achieved competit...
research
11/25/2022

Adaptive Attention Link-based Regularization for Vision Transformers

Although transformer networks are recently employed in various vision ta...
research
09/08/2022

Video Vision Transformers for Violence Detection

Law enforcement and city safety are significantly impacted by detecting ...
research
05/03/2022

Better plain ViT baselines for ImageNet-1k

It is commonly accepted that the Vision Transformer model requires sophi...
research
01/31/2022

Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations

Existing techniques for model inversion typically rely on hard-to-tune r...
research
10/06/2022

The Lie Derivative for Measuring Learned Equivariance

Equivariance guarantees that a model's predictions capture key symmetrie...
research
07/06/2023

Art Authentication with Vision Transformers

In recent years, Transformers, initially developed for language, have be...

Please sign up or login with your details

Forgot password? Click here to reset