# Robustness of Humans and Machines on Object Recognition with Extreme Image Transformations

arXiv: https://arxiv.org/abs/2205.05167 · HTML: https://mlsanity.com/paper/2205.05167/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 9 May 2022.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Human uncertainty makes classification more robust](https://mlsanity.com/paper/1908.07086/) (2019)
- [Learning to See by Looking at Noise](https://mlsanity.com/paper/2106.05963/) (2021)
- [Humans can decipher adversarial images](https://mlsanity.com/paper/1809.04120/) (2018)
- [Tracking Without Re-recognition in Humans and Machines](https://mlsanity.com/paper/2105.13351/) (2021)
- [The Challenge of Appearance-Free Object Tracking with Feedforward Neural Networks](https://mlsanity.com/paper/2110.02772/) (2021)

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

- [Extreme Image Transformations Affect Humans and Machines Differently](https://mlsanity.com/paper/2212.13967/) (2022)
- [Towards Explaining Satellite Based Poverty Predictions with Convolutional Neural Networks](https://mlsanity.com/paper/2312.00416/) (2023)
- [Extreme Image Transformations Facilitate Robust Latent Object Representations](https://mlsanity.com/paper/2310.07725/) (2023)

## Abstract (arXiv)

Recent neural network architectures have claimed to explain data from the human visual cortex. Their demonstrated performance is however still limited by the dependence on exploiting low-level features for solving visual tasks. This strategy limits their performance in case of out-of-distribution/adversarial data. Humans, meanwhile learn abstract concepts and are mostly unaffected by even extreme image distortions. Humans and networks employ strikingly different strategies to solve visual tasks. To probe this, we introduce a novel set of image transforms and evaluate humans and networks on an object recognition task. We found performance for a few common networks quickly decreases while humans are able to recognize objects with a high accuracy.