Search Results for author:
Found 3 papers, 0 papers with code
Adaptive Depth Networks with Skippable Sub-Paths
In this paper, we present an architectural pattern and training method for adaptive depth networks that can provide flexible accuracy-efficiency trade-offs in a single network.
Learning Deeply Shared Filter Bases for Efficient ConvNets
In the proposed ConvNet architecture, convolution layers are decomposed into a filter basis, that can be shared recursively, and layer-specific parts.
Deeply Shared Filter Bases for Parameter-Efficient Convolutional Neural Networks
In this paper, we present a recursive convolution block design and training method, in which a recursively shareable part, or a filter basis, is separated and learned while effectively avoiding the vanishing/exploding gradients problem during training.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
