# A case for robust translation tolerance in humans and CNNs. A commentary on Han et al

arXiv: https://arxiv.org/abs/2012.05950 · HTML: https://mlsanity.com/paper/2012.05950/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2020.

## Built on by (most cited first, 4 of 4)

- [Convolutional Neural Networks Are Not Invariant to Translation, but They Can Learn to Be](https://mlsanity.com/paper/2110.05861/) (2021)
- [Mixed Evidence for Gestalt Grouping in Deep Neural Networks](https://mlsanity.com/paper/2203.07302/) (2022)
- [Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training](https://mlsanity.com/paper/2110.01476/) (2021)
- [MindSet: Vision. A toolbox for testing DNNs on key psychological experiments](https://mlsanity.com/paper/2404.05290/) (2024)

## Abstract (arXiv)

Han et al. (2020) reported a behavioral experiment that assessed the extent to which the human visual system can identify novel images at unseen retinal locations (what the authors call "intrinsic translation invariance") and developed a novel convolutional neural network model (an Eccentricity Dependent Network or ENN) to capture key aspects of the behavioral results. Here we show that their analysis of behavioral data used inappropriate baseline conditions, leading them to underestimate intrinsic translation invariance. When the data are correctly interpreted they show near complete translation tolerance extending to 14deg in some conditions, consistent with earlier work (Bowers et al., 2016) and more recent work Blything et al. (in press). We describe a simpler model that provides a better account of translation invariance.