Rethinking ML Papers Workshop at ICLR
We demonstrate how boundary treatment in convolutional networks can incur foveation effects: Impacted pixels have fewer ways to contribute to the computation than central pixels. Different padding mechanisms can either eliminate or aggravate these effects (Alsallakh et al. 2021). This is made obvious via a web-based interactive visualization, available at https://mind-the-pad.github.io/
Donglai Xiang, Timur Bagautdinov, Tuur Stuyck, Fabian Prada, Javier Romero, Weipeng Xu, Shunsuke Saito, Jingfan Guo, Breannan Smith, Takaaki Shiratori, Yaser Sheikh, Jessica Hodgins, Chenglei Wu
Ludwig Sidenmark, Mark Parent, Chi-Hao Wu, Joannes Chan, Michael Glueck, Daniel Wigdor, Tovi Grossman, Marcello Giordano
Xingyi Zhou, Rohit Girdhar, Armand Joulin, Philipp Krähenbühl, Ishan Misra
