Neuroscience and Neurobiology Commons^™

Using Deep Features To Predict Where People Look, Matthias Kümmerer, Matthias Bethge

MODVIS Workshop

When free-viewing scenes, the first few fixations of human observers are driven in part by bottom-up attention. We seek to characterize this process by extracting all information from images that can be used to predict fixation densities (Kuemmerer et al, PNAS, 2015). If we ignore time and observer identity, the average amount of information is slightly larger than 2 bits per image for the MIT 1003 dataset. The minimum amount of information is 0.3 bits and the maximum 5.2 bits. Before the rise of deep neural networks the best models were able to capture 1/3 of this information on average. …