SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.02632 · 2022

Network Pruning via Feature Shift Minimization

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

Channel pruning is widely used to reduce the complexity of deep network models. Recent pruning methods usually identify which parts of the network to discard by proposing a channel importance criterion. However, recent studies have shown that these criteria do not work well in all conditions. In this paper, we propose a novel Feature Shift Minimization (FSM) method to compress CNN models, which evaluates the feature shift by converging the information of both features and filters. Specifically, we first investigate the compression efficiency with some prevalent methods in different layer-depths and then propose the feature shift concept. Then, we introduce an approximation method to estimate the magnitude of the feature shift, since it is difficult to compute it directly. Besides, we present a distribution-optimization algorithm to compensate for the accuracy loss and improve the network compression efficiency. The proposed method yields state-of-the-art performance on various benchmark networks and datasets, verified by extensive experiments. Our codes are available at: https://github.com/lscgx/FSM.

For agents

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

get_harvested_code_for_paper("2207.02632")
get_code_for_paper("2207.02632")
have("2207.02632")

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

curl https://syntology.ai/api/ran/2207.02632.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.02632.svg)](https://syntology.ai/paper/2207.02632)

Connect an agent — have() is free.