English(EN) Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNs

新的CGS方法增强了适用于移动部署的大型卷积核CNN

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-27 04:00

研究人员引入了一种称为通道组共享（CGS）低秩近似的新技术，以提高大型卷积神经网络（CNN）在移动设备上部署的效率。该方法通过使用基于奇异值分解（SVD）的参数共享策略，专注于优化逐点卷积，而逐点卷积构成了这些网络中绝大多数的参数。CGS方法降低了存储成本和内存带宽压力，使得RepLKNet、ConvNeXt和SLaK等预训练的大型卷积核模型能够切实地部署在资源受限的边缘设备上。 AI

影响通过显著降低存储和内存需求，使得大型高性能CNN能够部署在移动设备上。

排序理由该集群包含一篇详细介绍提高CNN效率新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 29 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍提高CNN效率新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Hao Luo, Yiting Yang, Wenyi Zhao, Man Jiang, Zhijun Lin, Ghulam Mohiuddin, Ting Jiang, Kunming Luo, Zihao Zhang, Qingsen Yan, Guoqing Wang, Wei Dong, Peng Wang · 2026-08-27 04:00

面向大核CNN中用于移动端高效逐点卷积的组共享低秩近似

arXiv:2608.26069v1 Announce Type: new Abstract: Large-kernel Convolutional Neural Networks (CNNs) deliver remarkable performance in vision tasks by significantly expanding receptive fields, yet their quadratic parameter growth critically impedes storage-efficient edge deployment.…

本文如何被排名

报道来源 [1]

面向大核CNN中用于移动端高效逐点卷积的组共享低秩近似

相关实体

相关话题