December 08, 2021
When convolutional layers apply no padding, central pixels have more ways to contribute to the convolution than peripheral pixels. Such discrepancy grows exponentially with the number of layers, leading to implicit foveation of the input pixels. We show that this discrepancy can persist even when padding is applied. In particular, with the commonly-used zero-padding, foveation effects are significantly reduced but not eliminated. We explore how different aspects of convolution arithmetic impact the extent and magnitude of these effects, and elaborate on which alternative padding techniques can mitigate it. Finally, we compare our findings with foveation in human vision, suggesting that both effects possibly have similar nature and implications.
Publisher
NeurIPS SVRHM Workshop
July 23, 2024
Zecheng He, Bo Sun, Felix Xu, Haoyu Ma, Ankit Ramchandani, Vincent Cheung, Siddharth Shah, Anmol Kalia, Ning Zhang, Peizhao Zhang, Roshan Sumbaly, Peter Vajda, Animesh Sinha
July 23, 2024
July 23, 2024
Llama team
July 23, 2024
July 02, 2024
Yawar Siddiqui, Tom Monnier, Filippos Kokkinos, Mahendra Kariya, Yanir Kleiman, Emilien Garreau, Oran Gafni, Natalia Neverova, Andrea Vedaldi, Roman Shapovalov, David Novotny
July 02, 2024
July 02, 2024
Raphael Bensadoun, Tom Monnier, Yanir Kleiman, Filippos Kokkinos, Yawar Siddiqui, Mahendra Kariya, Omri Harosh, Roman Shapovalov, Emilien Garreau, Animesh Karnewar, Ang Cao, Idan Azuri, Iurii Makarov, Eric-Tuan Le, Antoine Toisoul, David Novotny, Oran Gafni, Natalia Neverova, Andrea Vedaldi
July 02, 2024
Product experiences
Foundational models
Product experiences
Latest news
Foundational models