Export Reviews, Discussions, Author Feedback and Meta-Reviews

This paper uses a convolutional network to generate textures with the aim of using this texture generation technique to generate stimuli that elicit predictable neural responses in different parts of the visual pathway, assuming it works like the model. They match the correlations of CNN activities of an image to a synthesized image up to some layer in a CNN. Hopefully this will lead to some fruitful experiments. From past work, it is obvious that generating an image constrained by some summary statistics of a deep net representation of a target image will have a greater resemblance to this target if more of the deep net representation summary statistics are used. This paper does a nice job of showing that convincing textures can be generated using this technique, and that by using statistics from more layers, the process improves.