Saved in:
Bibliographic Details
Main Authors: Li, Changhao, Li, Haoling, Xue, Mengqi, Fang, Gongfan, Zhou, Sheng, Feng, Zunlei, Wang, Huiqiong, Song, Mingli, Song, Jie
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.12315
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916573276536832
author Li, Changhao
Li, Haoling
Xue, Mengqi
Fang, Gongfan
Zhou, Sheng
Feng, Zunlei
Wang, Huiqiong
Song, Mingli
Song, Jie
author_facet Li, Changhao
Li, Haoling
Xue, Mengqi
Fang, Gongfan
Zhou, Sheng
Feng, Zunlei
Wang, Huiqiong
Song, Mingli
Song, Jie
contents Structural pruning has emerged as a promising approach for producing more efficient models. Nevertheless, the community suffers from a lack of standardized benchmarks and metrics, leaving the progress in this area not fully comprehended. To fill this gap, we present the first comprehensive benchmark, termed PruningBench, for structural pruning. PruningBench showcases the following three characteristics: 1) PruningBench employs a unified and consistent framework for evaluating the effectiveness of diverse structural pruning techniques; 2) PruningBench systematically evaluates 16 existing pruning methods, encompassing a wide array of models (e.g., CNNs and ViTs) and tasks (e.g., classification and detection); 3) PruningBench provides easily implementable interfaces to facilitate the implementation of future pruning methods, and enables the subsequent researchers to incorporate their work into our leaderboards. We provide an online pruning platform for customizing pruning tasks and reproducing all results in this paper. Leaderboard results can also be available.
format Preprint
id arxiv_https___arxiv_org_abs_2406_12315
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Comprehensive Study of Structural Pruning for Vision Models
Li, Changhao
Li, Haoling
Xue, Mengqi
Fang, Gongfan
Zhou, Sheng
Feng, Zunlei
Wang, Huiqiong
Song, Mingli
Song, Jie
Artificial Intelligence
Structural pruning has emerged as a promising approach for producing more efficient models. Nevertheless, the community suffers from a lack of standardized benchmarks and metrics, leaving the progress in this area not fully comprehended. To fill this gap, we present the first comprehensive benchmark, termed PruningBench, for structural pruning. PruningBench showcases the following three characteristics: 1) PruningBench employs a unified and consistent framework for evaluating the effectiveness of diverse structural pruning techniques; 2) PruningBench systematically evaluates 16 existing pruning methods, encompassing a wide array of models (e.g., CNNs and ViTs) and tasks (e.g., classification and detection); 3) PruningBench provides easily implementable interfaces to facilitate the implementation of future pruning methods, and enables the subsequent researchers to incorporate their work into our leaderboards. We provide an online pruning platform for customizing pruning tasks and reproducing all results in this paper. Leaderboard results can also be available.
title A Comprehensive Study of Structural Pruning for Vision Models
topic Artificial Intelligence
url https://arxiv.org/abs/2406.12315