<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Neighborhood Attention on Noureddine RAMDI</title><link>https://ramdi.fr/tags/neighborhood-attention/</link><description>Recent content in Neighborhood Attention on Noureddine RAMDI</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 06 Jul 2026 15:16:10 +0000</lastBuildDate><atom:link href="https://ramdi.fr/tags/neighborhood-attention/index.xml" rel="self" type="application/rss+xml"/><item><title>SegMAN: Combining State Space Models with Neighborhood Attention for Semantic Segmentation</title><link>https://ramdi.fr/github-stars/segman-combining-state-space-models-with-neighborhood-attention-for-semantic-segmentation/</link><pubDate>Mon, 06 Jul 2026 15:15:52 +0000</pubDate><guid>https://ramdi.fr/github-stars/segman-combining-state-space-models-with-neighborhood-attention-for-semantic-segmentation/</guid><description>SegMAN blends State Space Models and Neighborhood Attention within a hybrid encoder-decoder for semantic segmentation, balancing long-range context with local detail. It achieves competitive mIoU on ADE20K with models from 6.4M to 92.6M parameters.</description></item></channel></rss>