PulseAugur
实时 18:06:27
English(EN) Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks

新方法修复剪枝后的稀疏视觉网络

研究人员开发了一种新颖的、无需训练的自适应信号复苏(ASR)方法,用于修复剪枝后的稀疏视觉网络。ASR通过逐通道的粒度进行校正,解决了高稀疏度模型中出现的精度下降问题,这与以往的逐层方法不同。该技术估计并稳定每个输出通道的方差匹配校正,显著提高了高稀疏度场景下的性能。例如,在CIFAR-10数据集上,ASR在90%稀疏度下将ResNet-50的top-1准确率恢复到55.6%,相比现有方法有了显著提升。 AI

影响 提高了剪枝视觉模型的准确性,可能有助于在资源受限设备上更有效地部署。

排序理由 该集群包含一篇详细介绍修复稀疏视觉网络新方法的学术论文。

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]

  1. arXiv cs.LG TIER_1 English(EN) · Minxuan Hu ·

    Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks

    One-shot magnitude pruning can cause severe accuracy collapse in the high-sparsity regime, even when the pruning mask preserves the largest weights. We argue that this failure reflects a granularity mismatch in post-pruning repair. Under global magnitude pruning, nearly collapsed…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks

    One-shot magnitude pruning can cause severe accuracy collapse in the high-sparsity regime, even when the pruning mask preserves the largest weights. We argue that this failure reflects a granularity mismatch in post-pruning repair. Under global magnitude pruning, nearly collapsed…