Papers › Ultimate tensorization: compressing convolutional and FC layers alike

Ultimate tensorization: compressing convolutional and FC layers alike

10 Nov 2016arXiv:1611.03214archive 2025-07-28

Timur Garipov, Dmitry Podoprikhin, Alexander Novikov, Dmitry Vetrov

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

timgaripov/TensorNet-TF officialmentioned in papermentioned on GitHubtf report
Gyiming/MobileSLAM mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections