Human perception in computer vision
arXiv:1701.04674
Abstract
Computer vision has made remarkable progress in recent years. Deep neural network (DNN) models optimized to identify objects in images exhibit unprecedented task-trained accuracy and, remarkably, some generalization ability: new visual problems can now be solved more easily based on previous learning. Biological vision (learned in life and through evolution) is also accurate and general-purpose. Is it possible that these different learning regimes converge to similar problem-dependent optimal computations? We therefore asked whether the human system-level computation of visual perception has DNN correlates and considered several anecdotal test cases. We found that perceptual sensitivity to image changes has DNN mid-computation correlates, while sensitivity to segmentation, crowding and shape has DNN end-computation correlates. Our results quantify the applicability of using DNN computation to estimate perceptual loss, and are consistent with the fascinating theoretical view that properties of human perception are a consequence of architecture-independent visual learning.
Under review as a conference paper at ICLR 2017
References in corpus (5)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition
- Object Detectors Emerge in Deep Scene CNNs
- What makes ImageNet good for transfer learning?
- Examining Representational Similarity in ConvNets and the Primate Visual Cortex