Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟭𝟭𝟰 Computer Vision Learning 𝗠𝗲𝗱𝗶𝗰𝗮𝗹 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿: Gated Axial-Attention for Medical Image Segmentation by Johns Hopkins University Follow me for similar post : 🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in arXiv 2021 with over 4 citations. 🔸 Outperform Unet, FCN and Unet++ ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/e26DDzU code : https://lnkd.in/eAZDbjz ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸It different from medical image segmentation model such as Networks like U-Net [ronneberger2015u], V-Net [milletari2016v], 3D U-Net [cciccek20163d], Res-UNet [xiao2018weighted], Dense-UNet [li2018h], Y-Net [mehta2018net], U-Net++ [zhou2018unet++], KiU-Net [valanarasu2020kiu, valanarasu2020kiu1] and U-Net3+. 🔸Medical Transformer (MedT) uses gated axial attention layer as the basic building block and uses LoGo strategy for training. MedT has two branches - a global branch and local branch. The input to both of these branches are the feature maps extracted from an initial conv block. #computervision #artificialintelligence #deeplearning