<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Gang Yang | ViLab</title>
    <link>https://vilab.team/author/gang-yang/</link>
      <atom:link href="https://vilab.team/author/gang-yang/index.xml" rel="self" type="application/rss+xml" />
    <description>Gang Yang</description>
    <generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Sun, 24 Mar 2024 00:00:00 +0000</lastBuildDate>
    <image>
      <url>https://vilab.team/media/icon_hu2896232876136423579.png</url>
      <title>Gang Yang</title>
      <link>https://vilab.team/author/gang-yang/</link>
    </image>
    
    <item>
      <title>Tmformer: Token merging transformer for brain tumor segmentation with missing modalities</title>
      <link>https://vilab.team/publication/tmformer-token-merging-transformer-for-brain-tumor-segmentat/</link>
      <pubDate>Sun, 24 Mar 2024 00:00:00 +0000</pubDate>
      <guid>https://vilab.team/publication/tmformer-token-merging-transformer-for-brain-tumor-segmentat/</guid>
      <description>&lt;p&gt;本文提出 TMFormer，一种用于缺失模态脑肿瘤分割的 Token 合并 Transformer。该方法通过提取并合并可用模态为更紧凑的 token 序列，解决现有方法以零图填充缺失模态带来的特征偏差与冗余计算问题。其核心包括单模态 Token 合并块（UMB）和多模态 Token 合并块（MMB），分别增强单模态表示并缓解多模态融合偏差。在 BraTS 2018 和 2020 数据集上的实验表明，TMFormer 在缺失模态场景下优于现有方法。&lt;/p&gt;
</description>
    </item>
    
  </channel>
</rss>
