A Comparison of Equivariant Vision Models with ImageNet Pre-training

Published: 29 Nov 2023, Last Modified: 29 Nov 2023NeurReps 2023 PosterEveryoneRevisionsBibTeX
Keywords: Vision, Equivariance, Pre-training
TL;DR: We provide implementations of equivariant vision models with ImageNet pretrained weights for other researchers to use.
Abstract: Neural networks pre-trained on large datasets provide useful embeddings for downstream tasks and allow researchers to iterate with less compute. For computer vision tasks, ImageNet pre-trained models can be easily downloaded for fine-tuning. However, no such pre-trained models are available that are equivariant to image transformations. In this work, we implement several equivariant versions of the residual network architecture and publicly release the weights after training on ImageNet. Additionally, we perform a comparison of enforced vs. learned equivariance in the largest data regime to date.
Submission Track: Extended Abstract
Submission Number: 25