Human uncertainty makes classification more robust
By: Researcher
Disclaimer: The provided code links for this paper are external links. Science Nest has no responsibility for the accuracy, legality or content of these links. Also, by downloading this code(s), you agree to comply with the terms of use as set out by the author(s) of the code(s).
Please contact us in case of a broken link from here
| Authors | Thomas L. Griffiths, Olga Russakovsky, Ruairidh M. Battleday, Joshua C. Peterson |
| Journal/Conference Name | ICCV 2019 10 |
| Paper Category | Artificial Intelligence |
| Paper Abstract | The classification performance of deep neural networks has begun to asymptote at near-perfect levels. However, their ability to generalize outside the training set and their robustness to adversarial attacks have not. In this paper, we make progress on this problem by training with full label distributions that reflect human perceptual uncertainty. We first present a new benchmark dataset which we call CIFAR10H, containing a full distribution of human labels for each image of the CIFAR10 test set. We then show that, while contemporary classifiers fail to exhibit human-like uncertainty on their own, explicit training on our dataset closes this gap, supports improved generalization to increasingly out-of-training-distribution test datasets, and confers robustness to adversarial attacks. |
| Date of publication | 2019 |
| Code Programming Language | Unspecified |
| Comment |
Copyright Researcher 2022