arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.07086cs.CV
收藏

人类的不确定性使分类更加鲁棒

Human uncertainty makes classification more robust

Princeton University(普林斯顿大学)

Joshua C. Peterson, Ruairidh M. Battleday, Thomas L. Griffiths, Olga Russakovsky

摘要:

深度神经网络的分类性能已经开始接近完美水平。然而,它们在训练集之外的泛化能力和对对抗攻击的鲁棒性却没有。在本文中,我们通过使用反映人类感知不确定性的完整标签分布进行训练,在这个问题上取得了进展。我们首先提出了一个新的基准数据集,我们称之为CIFAR10H,包含CIFAR10测试集的每个图像的人类标签的完整分布。然后,我们表明,虽然当代分类器本身无法表现出类似人类的不确定性,但对我们数据集的显式训练弥补了这一差距,支持对越来越多的训练分布测试数据集的改进泛化,并赋予对抗攻击的鲁棒性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑