Robustness Of Humans And Machines On Object Recognition With Extreme Image Transformations

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

**arXiv ID:** 2205.05167
**Authors:** Dakarai Crowder, Girik Malik
**Published:** 2022-05-09T17:15:54Z
**Abstract:**
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.

## Skill Description

This skill is generated from the arXiv paper: Robustness of Humans and Machines on Object Recognition with Extreme Image Transformations (2205.05167).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2205.05167](http://arxiv.org/abs/2205.05167v2)