تقرير
Differentiable Transportation Pruning
| العنوان: | Differentiable Transportation Pruning |
|---|---|
| المؤلفون: | Li, Yunqiang, van Gemert, Jan C., Hoefler, Torsten, Moons, Bert, Eleftheriou, Evangelos, Verhoef, Bram-Ernst |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | Deep learning algorithms are increasingly employed at the edge. However, edge devices are resource constrained and thus require efficient deployment of deep neural networks. Pruning methods are a key tool for edge deployment as they can improve storage, compute, memory bandwidth, and energy usage. In this paper we propose a novel accurate pruning technique that allows precise control over the output network size. Our method uses an efficient optimal transportation scheme which we make end-to-end differentiable and which automatically tunes the exploration-exploitation behavior of the algorithm to find accurate sparse sub-networks. We show that our method achieves state-of-the-art performance compared to previous pruning methods on 3 different datasets, using 5 different models, across a wide range of pruning ratios, and with two types of sparsity budgets and pruning granularities. Comment: ICCV 2023 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2307.08483 |
| رقم الأكسشن: | edsarx.2307.08483 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |