LGNov 10, 2016

Ultimate tensorization: compressing convolutional and FC layers alike

arXiv:1611.03214v1203 citations
Originality Incremental advance
AI Analysis

This work addresses efficiency issues in neural networks for image recognition, but it is incremental as it builds on prior tensor factorization methods.

The paper tackled the problem of high computational and memory complexity in convolutional neural networks by compressing convolutional layers using a tensor factorization method, achieving an 80x network compression rate with a 1.1% accuracy drop on CIFAR-10.

Convolutional neural networks excel in image recognition tasks, but this comes at the cost of high computational and memory complexity. To tackle this problem, [1] developed a tensor factorization framework to compress fully-connected layers. In this paper, we focus on compressing convolutional layers. We show that while the direct application of the tensor framework [1] to the 4-dimensional kernel of convolution does compress the layer, we can do better. We reshape the convolutional kernel into a tensor of higher order and factorize it. We combine the proposed approach with the previous work to compress both convolutional and fully-connected layers of a network and achieve 80x network compression rate with 1.1% accuracy drop on the CIFAR-10 dataset.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes