<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Unet on Noureddine RAMDI</title><link>https://ramdi.fr/tags/unet/</link><description>Recent content in Unet on Noureddine RAMDI</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 23 May 2026 20:41:27 +0000</lastBuildDate><atom:link href="https://ramdi.fr/tags/unet/index.xml" rel="self" type="application/rss+xml"/><item><title>SAM3-UNet: Adapting Meta's SAM3 for efficient dense prediction with a lightweight U-Net decoder</title><link>https://ramdi.fr/github-stars/sam3-unet-adapting-meta-s-sam3-for-efficient-dense-prediction-with-a-lightweight-u-net-decoder/</link><pubDate>Sat, 23 May 2026 20:41:14 +0000</pubDate><guid>https://ramdi.fr/github-stars/sam3-unet-adapting-meta-s-sam3-for-efficient-dense-prediction-with-a-lightweight-u-net-decoder/</guid><description>SAM3-UNet adapts Meta&amp;rsquo;s SAM3 foundation model for dense prediction tasks using a parameter-efficient adapter and U-Net decoder, enabling training under 6 GB GPU memory.</description></item></channel></rss>