PulseAugur
中
实时 05:14:31

新的PTQ方法增强了Vision Transformer在边缘设备的效率

作者 PulseAugur 编辑部 · [2 个来源] ·

两篇新研究论文介绍了用于Vision Transformer（ViTs）的先进训练后量化（PTQ）技术，以提高在资源受限设备上的效率。MixFrag通过估计组件脆弱性并将比特分配制定为背包问题，专注于自适应的层级精度分配，在ImageNet-1K上取得了有竞争力的性能，并在COCO目标检测上取得了最先进的结果。DopQ-ViT通过将量化与激活分布对齐并处理异常值来解决性能下降问题，提出了一种Tan量化器和一种MAD引导的最优缩放因子，在分类和检测任务上优于之前的PTQ方法。 AI

影响 这些技术可以实现更高效的部署，将先进的Vision Transformer模型部署到计算资源有限的边缘设备上。

排序理由 两篇在arXiv上发表的学术论文，详细介绍了Vision Transformer的训练后量化新方法。

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 →

新的PTQ方法增强了Vision Transformer在边缘设备的效率

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
Research
两篇在arXiv上发表的学术论文，详细介绍了Vision Transformer的训练后量化新方法。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
64 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 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Md. Mehrab Hossain Opi, Robiul Islam Ryad, Md. Umar Faruk ·

    MixFrag：面向 Vision Transformers 的脆弱性引导混合精度训练后量化

    arXiv:2607.28589v1 Announce Type: cross Abstract: Post-training quantization (PTQ) has emerged as an effective solution for deploying Vision Transformers (ViTs) on resource-constrained devices. However, existing PTQ methods typically employ uniform bit-widths across transformer c…

  2. arXiv cs.CV TIER_1 English(EN) · Lianwei Yang, Haisong Gong, Haokun Lin, Yichen Wu, Caifeng Shan, Zhenan Sun, Qingyi Gu ·

    DopQ-ViT：面向分布友好和离群点感知的 Vision Transformer 后训练量化

    arXiv:2408.03291v4 Announce Type: replace Abstract: Vision Transformers (ViTs) have gained significant attention, but their high computing cost limits the practical applications. While post-training quantization (PTQ) reduces model size and speeds up inference, it often degrades …

相关实体

相关话题