English(EN) Denoised Variance-Based Pruning with Optimal Brain Bias Compensation

新的剪枝方法显著降低 Vision Transformer 的计算成本

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-19 04:00

研究人员开发了一种名为去噪方差基剪枝与最优脑偏差补偿 (DVBP + OB$^2$C) 的新方法，以降低 Vision Transformers (ViTs) 的计算开销。该技术利用随机矩阵理论过滤激活协方差中的噪声，以实现更鲁棒的神经元选择。DVBP + OB$^2$C 还利用为选择收集的相同统计数据来优化剩余权重，实现了最先进的免训练性能。实验表明，在 50% 的 MLP 剪枝下，该方法在各种架构上保留了超过 90% 的原始准确率，显著优于以前的方法。 AI

影响该方法可以实现大型 Vision Transformer 模型在边缘设备的更高效部署。

排序理由该集群包含一篇详细介绍新模型剪枝方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 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: 0 / 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新模型剪枝方法的论文。[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: 48 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Geon Tack Lee, Jaegul Choo, Kang Eun Jeon · 2026-08-19 04:00

基于最优脑偏置补偿的去噪方差剪枝

arXiv:2608.17657v1 Announce Type: new Abstract: Vision Transformers (ViTs) achieve state-of-the-art performance but carry massive computational overhead that restricts edge deployment. Although structural pruning has emerged as a key strategy to reduce these costs, existing metho…

本文如何被排名

报道来源 [1]

基于最优脑偏置补偿的去噪方差剪枝

相关实体

相关话题