arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.13852cs.CV
收藏

深度学习能识别细微的人类活动吗?

Can Deep Learning Recognize Subtle Human Activities?

Vincent Jacquot, Zhuofan Ying, Gabriel Kreiman

摘要:

深度学习推动了计算机视觉最近令人兴奋的进展,灌输了这些算法可以解决任何视觉任务的信念。然而,通常用于训练和测试计算机视觉算法的数据集具有普遍的混杂因素。这种偏差使得人们很难真正估计这些算法的性能,以及计算机视觉模型在训练分布之外的外推效果如何。在这项工作中,我们提出了一个新的动作分类挑战,该挑战在人类身上表现良好,但在最先进的深度学习模型中表现不佳。作为原理的证明,我们考虑三个示范性任务:喝酒,阅读和坐着。使用最先进的计算机视觉模型达到的最佳准确率分别为61.7%、62.8%和76.8%,而人类参与者在这三项任务中的准确率超过90%。我们提出了一种严格的方法来减少创建数据集时的混淆,以及比较人类与计算机视觉性能时的混淆。源代码和数据集是公开的。

英文摘要:

Deep Learning has driven recent and exciting progress in computer vision, instilling the belief that these algorithms could solve any visual task. Yet, datasets commonly used to train and test computer vision algorithms have pervasive confounding factors. Such biases make it difficult to truly estimate the performance of those algorithms and how well computer vision models can extrapolate outside the distribution in which they were trained. In this work, we propose a new action classification challenge that is performed well by humans, but poorly by state-of-the-art Deep Learning models. As a proof-of-principle, we consider three exemplary tasks: drinking, reading, and sitting. The best accuracies reached using state-of-the-art computer vision models were 61.7%, 62.8%, and 76.8%, respectively, while human participants scored above 90% accuracy on the three tasks. We propose a rigorous method to reduce confounds when creating datasets, and when comparing human versus computer vision performance. Source code and datasets are publicly available.

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。

↑