# Translation Insensitive CNNs

arXiv: https://arxiv.org/abs/1911.11238 · HTML: https://mlsanity.com/paper/1911.11238/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2019.

## Built on by (most cited first, 3 of 3)

- [Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Function](https://mlsanity.com/paper/2110.00899/) (2021)
- [Learning Defense Transformers for Counterattacking Adversarial Examples](https://mlsanity.com/paper/2103.07595/) (2021)
- [Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles](https://mlsanity.com/paper/2510.03224/) (2025)

## Abstract (arXiv)

We address the problem that state-of-the-art Convolution Neural Networks (CNN) classifiers are not invariant to small shifts. The problem can be solved by the removal of sub-sampling operations such as stride and max pooling, but at a cost of severely degraded training and test efficiency. We present a novel usage of Gaussian-Hermite basis to efficiently approximate arbitrary filters within the CNN framework to obtain translation invariance. This is shown to be invariant to small shifts, and preserves the efficiency of training. Further, to improve efficiency in memory usage as well as computational speed, we show that it is still possible to sub-sample with this approach and retain a weaker form of invariance that we call translation insensitivity, which leads to stability with respect to shifts. We prove these claims analytically and empirically. Our analytic methods further provide a framework for understanding any architecture in terms of translation insensitivity, and provide guiding principles for design.