Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟭𝟭𝟵 Computer Vision Learning 𝗦𝘄𝗶𝗻 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿 : Hierarchical Vision Transformer using Shifted Windows by Microsoft Research Asia Follow me for similar post : 🇮🇳 Ashish Patel Interesting Facts : 🔸 It is published in 2021 arXiv papers with both about 4 citations 🔸 It outperforms ResNet-Y, EfficientNet, ViT, DeiT. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/gGjxkJG Code : https://lnkd.in/gK22rng ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 The proposed Swin Transformer builds hierarchical feature maps by merging image patches (shown in gray) in deeper layers and has linear computation complexity to input image size due to computation of self-attention only within each local window (shown in red). It can thus serve as a general-purpose backbone for both image classification and dense recognition tasks. 🔸In contrast, previous vision Transformers produce feature maps of a single low resolution and have quadratic computation complexity to input image size due to computation of self-attention globally. #computervision #artificialintelligence #deeplearning #innovation