663 citations · 829 across the 12 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.CV2022
Contrastive pretraining for semantic segmentation is robust to noisy positive pairs
Sebastian Gerard, Josephine Sullivan
Domain-specific variants of contrastive learning can construct positive pairs from two distinct in-domain images, while traditional methods just augment the same image twice. For e…
cs.LG2022★ 2 cited
Are All Linear Regions Created Equal?
Matteo Gamba, Adrian Chmielewski-Anders, Josephine Sullivan +2
The number of linear regions has been studied as a proxy of complexity for ReLU networks. However, the empirical success of network compression techniques like pruning and knowledg…