<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>稀疏注意力 | ViLab</title>
    <link>https://vilab.team/tag/%E7%A8%80%E7%96%8F%E6%B3%A8%E6%84%8F%E5%8A%9B/</link>
      <atom:link href="https://vilab.team/tag/%E7%A8%80%E7%96%8F%E6%B3%A8%E6%84%8F%E5%8A%9B/index.xml" rel="self" type="application/rss+xml" />
    <description>稀疏注意力</description>
    <generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Mon, 27 Oct 2025 00:00:00 +0000</lastBuildDate>
    <image>
      <url>https://vilab.team/media/icon_hu2896232876136423579.png</url>
      <title>稀疏注意力</title>
      <link>https://vilab.team/tag/%E7%A8%80%E7%96%8F%E6%B3%A8%E6%84%8F%E5%8A%9B/</link>
    </image>
    
    <item>
      <title>Dome-DETR: DETR with density-oriented feature-query manipulation for efficient tiny object detection</title>
      <link>https://vilab.team/publication/dome-detr-detr-with-density-oriented-feature-query-manipulat/</link>
      <pubDate>Mon, 27 Oct 2025 00:00:00 +0000</pubDate>
      <guid>https://vilab.team/publication/dome-detr-detr-with-density-oriented-feature-query-manipulat/</guid>
      <description>&lt;p&gt;本文提出 Dome-DETR，一种面向微小物体检测的高效框架。针对现有方法特征利用不充分和计算成本高的问题，引入轻量级密度聚焦提取器（DeFE）生成紧凑前景掩码，并基于掩码的窗口注意力稀疏化（MWAS）将计算资源集中于关键区域。同时提出渐进自适应查询初始化（PAQI），自适应调节查询分布，提升检测效率与精度。&lt;/p&gt;
</description>
    </item>
    
  </channel>
</rss>
