paper-with-me

Papers

Ultimate tensorization: compressing convolutional and FC layers alike

2016-11-10 · 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.

📄 PDF Abstract BibTeX arXiv:1611.03214

Code (2)

timgaripov/TensorNet-TF 공식 구현 tf
Gyiming/MobileSLAM tf

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Tensor network compressibility of convolutional models

2024-03-21 · Sukhbinder Singh, Saeed S. Jahromi, Roman Orus

Convolutional neural networks (CNNs) are one of the most widely used neural network architectures, showcasing state-of-the-art performance in computer vision tasks. Although larger CNNs generally exhibit higher accuracy,…

image-classificationImage Classification

Fast Tensorization of Neural Networks via Slice-wise Feature Distillation

2026-05-19 · Safa Hamreras, Sukhbinder Singh, Román Orús arxiv

We propose a scalable tensorization framework for neural network compression based on slice-wise feature distillation. Unlike conventional tensor decomposition methods that rely on costly global finetuning, our approach …

Neural Network Compression

T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensor

2019-04-04 · CVPR 2019 6 · Jean Kossaifi, Adrian Bulat, Georgios Tzimiropoulos, Maja Pantic

Recent findings indicate that over-parametrization, while crucial for successfully training deep neural networks, also introduces large amounts of redundancy. Tensor methods have the potential to efficiently parametrize …

Pose Estimation

EinSort: Sorting is All We Need for Tensorizing LLM

2026-06-07 · Toshiaki Koike-Akino, Jing Liu, Ye Wang arxiv

Tensor networks provide efficient representations for compressing large neural networks. By carefully designing shapes and topologies, they can significantly reduce memory and computational costs. However, identifying im…

Defensive Tensorization

2021-10-26 · Adrian Bulat, Jean Kossaifi, Sourav Bhattacharya, Yannis Panagakis 외

We propose defensive tensorization, an adversarial defence technique that leverages a latent high-order factorization of the network. The layers of a network are first expressed as factorized tensor layers. Tensor dropou…

Audio ClassificationClassificationimage-classificationImage Classification