Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟭𝟵𝟭 Computer Vision Learning 𝗘𝗮𝗴𝗹𝗲𝗘𝘆𝗲: Fast Sub-net Evaluation for Efficient Neural Network Pruning by Sun Yat-sen University Follow me for similar post :  🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in ECCV2020 with over 14 citations. 🔸 It outperforms Mobilenet v1, resnet etc. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/e3byeqE Code : https://lnkd.in/eFvhnVv ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Finding out the computational redundant part of a trained Deep Neural Network (DNN) is the key question that pruning algorithms target on. Many algorithms try to predict model performance of the pruned sub-nets by introducing various evaluation methods. But they are either inaccurate or very complicated for general application. 🔸 In this work, they present a pruning method called 𝗘𝗮𝗴𝗹𝗲𝗘𝘆𝗲, in which a simple yet efficient evaluation component based on 𝗮𝗱𝗮𝗽𝘁𝗶𝘃𝗲 𝗯𝗮𝘁𝗰𝗵 𝗻𝗼𝗿𝗺𝗮𝗹𝗶𝘇𝗮𝘁𝗶𝗼𝗻 is applied to unveil a strong correlation between different pruned DNN structures and their final settled accuracy. 🔸This strong correlation allows us to fast spot the pruned candidates with highest potential ac- curacy without actually fine-tuning them. This module is also general to plug-in and improve some existing pruning algorithms. EagleEye achieves better pruning performance than all of the studied pruning algorithms in our experiments. #computervision #artificialintelligence #data