Affiliation: Assistant professor at the Technical University Delft
Place: Large Lecture Room
The design of filter layers in a CNNs is a matter of trail and error where the filter-size in a single layer is typically hard-coded. Here I question this design. Instead of hard-coding we aim to learn the resolution. We do this by coupling resolution to the standard deviation of a Gaussian blur kernel, and then learn CNN filters by learning coefficients of a local differential Gaussian basis. Preliminary results show that global resolution can be learned by optimizing the standard deviation, and –in contrast to pixel filters CNNs– is robust to changing scales.