Popularity Prediction for Social Media over Arbitrary Time Horizons
Daniel Haimovich, Dima Karamshuk, Thomas Leeper, Evgeniy Riabenko, Milan Vojnovic
Shared Visual Representations in Human and Machine Intelligence (SVRHM) Workshop at NeurIPS
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.
Daniel Haimovich, Dima Karamshuk, Thomas Leeper, Evgeniy Riabenko, Milan Vojnovic
Liqi Yan, Qifan Wang, Yiming Cu, Fuli Feng, Xiaojun Quan, Xiangyu Zhang, Dongfang Liu
Patrick Lewis, Barlas Oğuz, Wenhan Xiong, Fabio Petroni, Wen-tau Yih, Sebastian Riedel