# CIFAR10 to Compare Visual Recognition Performance between Deep Neural Networks and Humans

arXiv: https://arxiv.org/abs/1811.07270 · HTML: https://mlsanity.com/paper/1811.07270/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2018.

## Built on by (most cited first, 14 of 14)

- [Adversarial Policies Beat Superhuman Go AIs](https://mlsanity.com/paper/2211.00241/) (2022)
- [Continuous Thought Machines](https://mlsanity.com/paper/2505.05522/) (2025)
- [If a Human Can See It, So Should Your System: Reliability Requirements for Machine Vision Components](https://mlsanity.com/paper/2202.03930/) (2022)
- [Asymmetric Certified Robustness via Feature-Convex Neural Networks](https://mlsanity.com/paper/2302.01961/) (2023)
- [Automated Extraction of Energy Systems Information from Remotely Sensed Data: A Review and Analysis](https://mlsanity.com/paper/2202.12939/) (2022)
- [Expected Grad-CAM: Towards gradient faithfulness](https://mlsanity.com/paper/2406.01274/) (2024)
- [Active Learning Under Malicious Mislabeling and Poisoning Attacks](https://mlsanity.com/paper/2101.00157/) (2021)
- [Assessing Visually-Continuous Corruption Robustness of Neural Networks Relative to Human Performance](https://mlsanity.com/paper/2402.19401/) (2024)
- [Know2Vec: A Black-Box Proxy for Neural Network Retrieval](https://mlsanity.com/paper/2412.16251/) (2024)
- [Knowledge-based XAI through CBR: There is more to explanations than models can tell](https://mlsanity.com/paper/2108.10363/) (2021)
- [Cliff-Learning](https://mlsanity.com/paper/2302.07348/) (2023)
- [FedCME: Client Matching and Classifier Exchanging to Handle Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2307.08574/) (2023)
- [Hybrid of DiffStride and Spectral Pooling in Convolutional Neural Networks](https://mlsanity.com/paper/2401.09008/) (2024)
- [LSP Framework: A Compensatory Model for Defeating Trigger Reverse Engineering via Label Smoothing Poisoning](https://mlsanity.com/paper/2404.12852/) (2024)

## Abstract (arXiv)

Visual object recognition plays an essential role in human daily life. This ability is so efficient that we can recognize a face or an object seemingly without effort, though they may vary in position, scale, pose, and illumination. In the field of computer vision, a large number of studies have been carried out to build a human-like object recognition system. Recently, deep neural networks have shown impressive progress in object classification performance, and have been reported to surpass humans. Yet there is still lack of thorough and fair comparison between humans and artificial recognition systems. While some studies consider artificially degraded images, human recognition performance on dataset widely used for deep neural networks has not been fully evaluated. The present paper carries out an extensive experiment to evaluate human classification accuracy on CIFAR10, a well-known dataset of natural images. This then allows for a fair comparison with the state-of-the-art deep neural networks. Our CIFAR10-based evaluations show very efficient object recognition of recent CNNs but, at the same time, prove that they are still far from human-level capability of generalization. Moreover, a detailed investigation using multiple levels of difficulty reveals that easy images for humans may not be easy for deep neural networks. Such images form a subset of CIFAR10 that can be employed to evaluate and improve future neural networks.