How Is Scene Recognition in a Convolutional Network Related to that in the Human Visual System?
This study is an analysis of scene recognition in a pre-trained convolutional network, to evaluate the information the network uses to distinguish scene categories. We are particularly interested in how the network is related to various areas in the human brain that are involved in different modes of scene recognition. Results of several experiments suggest that the convolutional network relies heavily on objects and fine features, similar to the lateral occipital complex (LOC) in the brain, but less on large-scale scene layout. This suggests that future scene-processing convolutional networks might be made more brain-like by adding parallel components that are more sensitive to arrangement of simple forms.
KeywordsConvolutional neural networks (CNNs) Scene recognition Human visual system
Supported by CFI & OIT infrastructure funds, the Canada Research Chairs program, NSERC Discovery grants 261453 and 296878, ONR grant N000141310419, AFOSR grant FA8655-13-1-3084 and OGS.
- 5.Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1097–1105 (2012)Google Scholar
- 7.Oliva, A.: Scene perception. In: Werner, J.S., Chalupa, L.M. (eds.) The New Visual Neurosciences, pp. 725–732. MIT Press, Cambridge (2014)Google Scholar
- 10.Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., Oliva, A.: Learning deep features for scene recognition using places database. Adv. Neural Inf. Process. Syst. 27, 487–495 (2014)Google Scholar