Ashish Patel 🇮🇳’s Post

Day-9 Computer Vision Learning 𝗗𝗿𝗼𝗽𝗕𝗹𝗼𝗰𝗸: A 𝗥𝗲𝗴𝘂𝗹𝗮𝗿𝗶𝘇𝗮𝘁𝗶𝗼𝗻 𝗠𝗲𝘁𝗵𝗼𝗱 for Convolutional Networks (Image Classification) By Google 𝗗𝗿𝗼𝗽𝗕𝗹𝗼𝗰𝗸 published in 2018 NeurIPS with over 200 citations --------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵: https://lnkd.in/erBPDYb 𝗢𝗳𝗳𝗶𝗰𝗶𝗮𝗹 𝗖𝗼𝗱𝗲: https://lnkd.in/ejSuGaY 𝗧𝗲𝗻𝘀𝗼𝗿𝗙𝗹𝗼𝘄2 : https://lnkd.in/eXwGE6F 𝗞𝗲𝗿𝗮𝘀 : https://lnkd.in/eu9iFTu 𝗣𝘆𝘁𝗼𝗿𝗰𝗵 : https://lnkd.in/ePteTqY --------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🌅 Outperforms Dropout, DropPath from FractalNet, SpatialDropout, Cutout, AutoAugment, and Label Smoothing from Inception-v3 ⏩ DropBlock, a form of structured Dropout, is proposed where units in a contiguous region of a feature map are dropped together. ☀️Applying DropBlock in skip connections in addition to the convolution layers increases the accuracy. #innovation #artificialintelligence #computervision #india