Ashish Patel 🇮🇳’s Post

Day-75 Computer Vision Learning Auto-DeepLab : Hierarchical Neural Architecture Search for Semantic Image Segmentation by Google, John Hopkins University, Stanford University Follow me for similar post : 🇮🇳 Ashish Patel Interesting Facts : 🔸 It is published in 2019 CVPR, which has already got over 399 citations. 🔸 It Outperforms ResNet, DenseNet, Deeplabv3+, NASNet, AmoebaNet, PNASNet, DARTS, DPC. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/evrb324 Official Code : https://bit.ly/3llgguM pytorch : 1. https://bit.ly/3bRcSEX 2. https://bit.ly/3liYPuW 3. https://bit.ly/3rWxIbE ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 NAS usually uses transfer learning from low resolution images to high resolution images, and the best framework for semantic segmentation must be in high Resolution image runs. 🔸 Neural Architecture Search aims at automatically designing neural network architectures, hence minimizing human hours and efforts. #computervision #artificialintelligence