15 citations · 66 across the 17 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.CV2020★ 4 cited
Layer-Wise Data-Free CNN Compression
Maxwell Horton, Yanzi Jin, Ali Farhadi +1
We present a computationally efficient method for compressing a trained neural network without using real data. We break the problem of data-free network compression into independe…
cs.LG2020★ 8 cited
Supermasks in Superposition
Mitchell Wortsman, Vivek Ramanujan, Rosanne Liu +4
We present the Supermasks in Superposition (SupSup) model, capable of sequentially learning thousands of tasks without catastrophic forgetting. Our approach uses a randomly initial…