<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>InfoQ - Predictive Modeling</title>
    <link>https://www.infoq.com</link>
    <description>InfoQ Predictive Modeling feed</description>
    <item>
      <title>Unsupervised Object Detection and Semantic Segmentation Using Deep Learning</title>
      <link>https://www.infoq.com/news/2023/02/unsupervised-object-detection/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Predictive+Modeling</link>
      <description>&lt;img src="https://res.infoq.com/news/2023/02/unsupervised-object-detection/en/headerimage/unsupervised-object-detection-semantic-segmentation-deep-learning-header-1676292560237.jpg"/&gt;&lt;p&gt;Meta AI released CutLER, a state-of-the-art zero-shot unsupervised object detector which improves detection performance by over 2.7 times on 11 benchmark datasets for different domains like video frames, painting, sketches, etc. This model’s simplicity allows compatibility with different object-detection architectures across different domains.&lt;/p&gt; &lt;i&gt;By Bruno Santos&lt;/i&gt;</description>
      <category>Predictive Modeling</category>
      <category>Machine Learning</category>
      <category>Data</category>
      <category>Deep Learning</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>news</category>
      <pubDate>Tue, 14 Feb 2023 06:30:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2023/02/unsupervised-object-detection/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Predictive+Modeling</guid>
      <dc:creator>Bruno Santos</dc:creator>
      <dc:date>2023-02-14T06:30:00Z</dc:date>
      <dc:identifier>/news/2023/02/unsupervised-object-detection/en</dc:identifier>
    </item>
  </channel>
</rss>
