Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| 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 |