论文标题
人类和机器在物体识别上具有极端图像转换的鲁棒性
Robustness of Humans and Machines on Object Recognition with Extreme Image Transformations
论文作者
论文摘要
最近的神经网络体系结构声称可以解释人类视觉皮层的数据。然而，他们所证明的性能仍然受到利用低级功能来解决视觉任务的限制。在分发/对抗数据的情况下，此策略限制了其性能。同时，人类学习抽象概念，并且大多不受极端图像扭曲的影响。人类和网络采用截然不同的策略来解决视觉任务。为了探究这一点，我们介绍了一组新颖的图像转换，并在对象识别任务上评估人和网络。我们发现一些常见网络的性能很快降低了，而人类能够以很高的精度识别对象。
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.
