LAUSR

Holistic CNN Compression via Low-Rank Decomposition with Knowledge Transfer

Sign Up to like & get
recommendations!
0 Published in 2019 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"

DOI: 10.1109/tpami.2018.2873305

Abstract: Convolutional neural networks (CNNs) have achieved remarkable success in various computer vision tasks, which are extremely powerful to deal with massive training data by using tens of millions of parameters. However, CNNs often cost significant… read more here.

Keywords: rank decomposition; compression; cnn compression; low rank ... See more keywords