Ashish Patel 🇮🇳’s Post

Day-36 Computer Vision Learning Residual Attention Network — Attention-Aware Features (Image Classification) by SenseTime 商汤科技, Tsinghua University, Chinese University of Hong Kong (CUHK) and Beijing University of Posts and Telecommunications Follow me for similar post : 🇮🇳 Ashish Patel Interesting Facts : 🔸 It is published in 2017 #CVPR , which has already got over 1376 citations 🔸 Multiple attention module is stacked to generate attention-aware features. 🔸 Attention residual learning is used for very deep network. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eF4q22K pytorch: https://bit.ly/3rmDp1I keras : https://bit.ly/36KlH08 tensorflow: https://bit.ly/2MAPHVu ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 It outperforms Pre-Activation ResNet, WRN, Inception-ResNet, ResNeXt 🔸 Naive Attention Learning (NAL) leads to performance drop. 🔸 Residual Attention Network is 3 stage network. #computervision #artificialintelligence #analytics