GhostNetV3: Exploring the Training Strategies for Compact Models

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Zhenhua, Hao, Zhiwei, Han, Kai, Tang, Yehui, Wang, Yunhe
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910416919068672
author Liu, Zhenhua
Hao, Zhiwei
Han, Kai
Tang, Yehui
Wang, Yunhe
author_facet Liu, Zhenhua
Hao, Zhiwei
Han, Kai
Tang, Yehui
Wang, Yunhe
contents Compact neural networks are specially designed for applications on edge devices with faster inference speed yet modest performance. However, training strategies of compact models are borrowed from that of conventional models at present, which ignores their difference in model capacity and thus may impede the performance of compact models. In this paper, by systematically investigating the impact of different training ingredients, we introduce a strong training strategy for compact models. We find that the appropriate designs of re-parameterization and knowledge distillation are crucial for training high-performance compact models, while some commonly used data augmentations for training conventional models, such as Mixup and CutMix, lead to worse performance. Our experiments on ImageNet-1K dataset demonstrate that our specialized training strategy for compact models is applicable to various architectures, including GhostNetV2, MobileNetV2 and ShuffleNetV2. Specifically, equipped with our strategy, GhostNetV3 1.3$\times$ achieves a top-1 accuracy of 79.1% with only 269M FLOPs and a latency of 14.46ms on mobile devices, surpassing its ordinarily trained counterpart by a large margin. Moreover, our observation can also be extended to object detection scenarios. PyTorch code and checkpoints can be found at https://github.com/huawei-noah/Efficient-AI-Backbones/tree/master/ghostnetv3_pytorch.
format Preprint
id arxiv_https___arxiv_org_abs_2404_11202
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GhostNetV3: Exploring the Training Strategies for Compact Models
Liu, Zhenhua
Hao, Zhiwei
Han, Kai
Tang, Yehui
Wang, Yunhe
Computer Vision and Pattern Recognition
Compact neural networks are specially designed for applications on edge devices with faster inference speed yet modest performance. However, training strategies of compact models are borrowed from that of conventional models at present, which ignores their difference in model capacity and thus may impede the performance of compact models. In this paper, by systematically investigating the impact of different training ingredients, we introduce a strong training strategy for compact models. We find that the appropriate designs of re-parameterization and knowledge distillation are crucial for training high-performance compact models, while some commonly used data augmentations for training conventional models, such as Mixup and CutMix, lead to worse performance. Our experiments on ImageNet-1K dataset demonstrate that our specialized training strategy for compact models is applicable to various architectures, including GhostNetV2, MobileNetV2 and ShuffleNetV2. Specifically, equipped with our strategy, GhostNetV3 1.3$\times$ achieves a top-1 accuracy of 79.1% with only 269M FLOPs and a latency of 14.46ms on mobile devices, surpassing its ordinarily trained counterpart by a large margin. Moreover, our observation can also be extended to object detection scenarios. PyTorch code and checkpoints can be found at https://github.com/huawei-noah/Efficient-AI-Backbones/tree/master/ghostnetv3_pytorch.
title GhostNetV3: Exploring the Training Strategies for Compact Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.11202