Correspondence of Deep Neural Networks and the Brain for Visual Textures
By Md Nasir Uddin Laskar, L. S. Giraldo, Odelia Schwartz. 2018
20 citations recorded by the source corpus.
Deep convolutional neural networks (CNNs) trained on objects and scenes have shown intriguing ability to predict some response properties of visual cortical neurons. However, the factors and computations that give rise to such ability, and the role of intermediate processing stages in explaining changes that develop across areas of the cortical hierarchy, are poorly understood. We focused on the sensitivity to textures as a paradigmatic example, since recent neurophysiology experiments provide rich data pointing to texture sensitivity in secondary but not primary visual cortex. We developed a quantitative approach for selecting a subset of the neural unit population from the CNN that best describes the brain neural recordings. We found that the first two layers of the CNN showed qualitative and quantitative correspondence to the cortical data across a number of metrics. This compatibility was reduced for the architecture alone rather than the learned weights, for some other related hierarchical models, and only mildly in the absence of a nonlinear computation akin to local divisive normalization. Our results show that the CNN class of model is effective for capturing changes that develop across early areas of cortex, and has the potential to facilitate understanding of the computations that give rise to hierarchical processing in the brain.
Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Cognitive Neuroscience
- Matthias Bethge
- Robert Geirhos
- Wieland Brendel
- Felix Wichmann
- Claudio Michaelis
- Patrick Esser
- Axel Sauer
- Ekin Dogus Cubuk
In Computer Vision and Pattern Recognition
- Wieland Brendel
- Matthias Bethge
- Robert Geirhos
- Felix Wichmann
- Claudio Michaelis
- Luc Van Gool
- Trevor Darrell
- Bernt Schiele
Citations in the corpus
- ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness (2018, background): “…CNNs match texture appearance for humans (Wallis et al., 2017), and their predictive power for neural responses along the human ventral stream appears to be largely due to human-like texture representations, but not human-like contour representations (Laskar et al., 2018; Long & Konkle, 2018).”