English(EN) Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware

Smart Scissor框架在提高精度的同时大幅降低CNN计算成本

作者 PulseAugur 编辑部 · [2 个来源] · 2026-07-08 02:12

研究人员开发了一个名为Smart Scissor的新颖框架，旨在降低卷积神经网络（CNN）在嵌入式硬件上的计算需求。该方法结合了动态图像裁剪以最小化空间冗余，以及跨深度、宽度和分辨率进行CNN压缩的复合收缩策略。实验表明，在ImageNet-1K数据集上，Smart Scissor可以将ResNet50的计算成本降低41.5%，同时将top-1准确率提高0.3%。此外，它在同等计算成本下实现了4.1%的更高top-1准确率，优于当前最先进的CNN压缩框架HRank。 AI

影响这项研究提供了一种显著降低CNN计算需求的方法，使其在资源受限的嵌入式设备上部署更加可行。

排序理由详细介绍CNN压缩新方法的学术论文。[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 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.LG TIER_1 English(EN) · Hao Kong, Di Liu, Shuo Huai, Xiangzhong Luo, Weichen Liu, Ravi Subramaniam, Christian Makaya, Qian Lin · 2026-07-09 04:00

Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware

arXiv:2607.06915v1 Announce Type: cross Abstract: Scaling down the resolution of input images can greatly reduce the computational overhead of convolutional neural networks (CNNs), which is promising for edge AI. However, as an image usually contains much spatial redundancy, e.g.…
arXiv cs.CV TIER_1 English(EN) · Qian Lin · 2026-07-08 02:12

Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware

Scaling down the resolution of input images can greatly reduce the computational overhead of convolutional neural networks (CNNs), which is promising for edge AI. However, as an image usually contains much spatial redundancy, e.g., background pixels, directly shrinking the whole …

报道来源 [2]

Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware

Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware

相关实体

相关话题