Can the early human visual system compete with Deep Neural Networks?
This work addresses the problem of robustness in AI vision systems for applications like autonomous vehicles or medical imaging, though it is incremental as it builds on prior comparisons.
The study compared the early human visual system, limited to 100ms display time, with state-of-the-art deep neural networks on classifying distorted images, finding that humans outperform networks under blurry and noisy conditions.
We study and compare the human visual system and state-of-the-art deep neural networks on classification of distorted images. Different from previous works, we limit the display time to 100ms to test only the early mechanisms of the human visual system, without allowing time for any eye movements or other higher level processes. Our findings show that the human visual system still outperforms modern deep neural networks under blurry and noisy images. These findings motivate future research into developing more robust deep networks.