# What Affects Learned Equivariance in Deep Image Recognition Models?

Source: [What Affects Learned Equivariance in Deep Image Recognition Models?](<https://www.sota2.com/research/paper/68fa6f091e209131cea43745>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:11:39.114Z

Authors: Robert-Jan Bruintjes, Tomasz Motyka, Jan van Gemert

Published: 2023-04-05T17:54:25.000Z

## Abstract

Equivariance w.r.t. geometric transformations in neural networks improves data efficiency, parameter efficiency and robustness to out-of-domain perspective shifts. When equivariance is not designed into a neural network, the network can still learn equivariant functions from the data. We quantify this learned equivariance, by proposing an improved measure for equivariance. We find evidence for a correlation between learned translation equivariance and validation accuracy on ImageNet. We therefore investigate what can increase the learned equivariance in neural networks, and find that data augmentation, reduced model capacity and inductive bias in the form of convolutions induce higher learned equivariance in neural networks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2304.02628>)

[PDF](<https://arxiv.org/pdf/2304.02628.pdf>)