175 citations · 175 across the 2 of their papers we have counts for
2 papers
cs.CV2021
Temporally stable video segmentation without video annotations
Aharon Azulay, Tavi Halperin, Orestis Vantzos +2
Temporally consistent dense video annotations are scarce and hard to collect. In contrast, image segmentation datasets (and pre-trained models) are ubiquitous, and easier to label…
cs.CV2018★ 175 cited
Why do deep convolutional networks generalize so poorly to small image transformations?
Aharon Azulay, Yair Weiss
Convolutional Neural Networks (CNNs) are commonly assumed to be invariant to small image transformations: either because of the convolutional architecture or because they were trai…