# Do Deep Neural Networks Suffer from Crowding?

arXiv: https://arxiv.org/abs/1706.08616 · HTML: https://mlsanity.com/paper/1706.08616/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2017.

## Built on by (most cited first, 7 of 7)

- [Contemplating real-world object classification](https://mlsanity.com/paper/2103.05137/) (2021)
- [Is current research on adversarial robustness addressing the right problem?](https://mlsanity.com/paper/2208.00539/) (2022)
- [The Foes of Neural Network's Data Efficiency Among Unnecessary Input Dimensions](https://mlsanity.com/paper/2107.06409/) (2021)
- [FovEx: Human-Inspired Explanations for Vision Transformers and Convolutional Neural Networks](https://mlsanity.com/paper/2408.02123/) (2024)
- [Predicting decision-making in the future: Human versus Machine](https://mlsanity.com/paper/2110.04465/) (2021)
- [Diverse, Difficult, and Odd Instances (D2O): A New Test Set for Object Classification](https://mlsanity.com/paper/2301.12527/) (2023)
- [Breast Cancer classification by adaptive weighted average ensemble of previously trained models](https://mlsanity.com/paper/2311.13206/) (2023)

## Abstract (arXiv)

Crowding is a visual effect suffered by humans, in which an object that can be recognized in isolation can no longer be recognized when other objects, called flankers, are placed close to it. In this work, we study the effect of crowding in artificial Deep Neural Networks for object recognition. We analyze both standard deep convolutional neural networks (DCNNs) as well as a new version of DCNNs which is 1) multi-scale and 2) with size of the convolution filters change depending on the eccentricity wrt to the center of fixation. Such networks, that we call eccentricity-dependent, are a computational model of the feedforward path of the primate visual cortex. Our results reveal that the eccentricity-dependent model, trained on target objects in isolation, can recognize such targets in the presence of flankers, if the targets are near the center of the image, whereas DCNNs cannot. Also, for all tested networks, when trained on targets in isolation, we find that recognition accuracy of the networks decreases the closer the flankers are to the target and the more flankers there are. We find that visual similarity between the target and flankers also plays a role and that pooling in early layers of the network leads to more crowding. Additionally, we show that incorporating the flankers into the images of the training set does not improve performance with crowding.