研究人员开发了两个新框架PSViT和PrimeSVT，用于压缩脉冲视觉Transformer（SViTs），使其更适合资源受限的设备。PSViT采用结构化剪枝方法，包括通道级滤波器剪枝和敏感性分析，以减小模型尺寸并保持准确性。PrimeSVT提供了一种自动化的、内存感知的方法，该方法根据层大小和鲁棒性优先进行压缩，在不牺牲性能的情况下实现显著的内存节省。 AI
影响 能够更有效地在边缘设备上部署先进的视觉模型。
排序理由 两篇介绍模型压缩新方法的学术论文。
在 arXiv cs.NE (Neural & Evolutionary) 阅读 →
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2606.03257v1 Announce Type: cross Abstract: Spiking Vision Transformer (SViT) models are promising low-power ViT models for solving vision-based tasks with state-of-the-art performance. However, their large sizes limit their deployments for resource-constrained embedded pla…
arXiv:2606.03428v1 Announce Type: cross Abstract: The large sizes of Spiking Vision Transformers (SViTs) still hinder their embedded implementation, highlighting the need for model compression. State-of-the-art works compress SViT models through unstructured pruning, which needs …
The large sizes of Spiking Vision Transformers (SViTs) still hinder their embedded implementation, highlighting the need for model compression. State-of-the-art works compress SViT models through unstructured pruning, which needs specialized hardware accelerators for their specif…
Spiking Vision Transformer (SViT) models are promising low-power ViT models for solving vision-based tasks with state-of-the-art performance. However, their large sizes limit their deployments for resource-constrained embedded platforms, underscoring the needs of model compressio…