SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.12110 · 2020

Tensor Reordering for CNN Compression

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We show how parameter redundancy in Convolutional Neural Network (CNN) filters can be effectively reduced by pruning in spectral domain. Specifically, the representation extracted via Discrete Cosine Transform (DCT) is more conducive for pruning than the original space. By relying on a combination of weight tensor reshaping and reordering we achieve high levels of layer compression with just minor accuracy loss. Our approach is applied to compress pretrained CNNs and we show that minor additional fine-tuning allows our method to recover the original model performance after a significant parameter reduction. We validate our approach on ResNet-50 and MobileNet-V2 architectures for ImageNet classification task.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2010.12110")
get_code_for_paper("2010.12110")
have("2010.12110")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2010.12110.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2010.12110.svg)](https://syntology.ai/paper/2010.12110)

Connect an agent — have() is free.