Ashish Patel 🇮🇳’s Post

Day-87 Computer Vision Learning FCIS — Winner in 2016 COCO Segmentation (Instance Segmentation) by Tsinghua University and Microsoft Research Asia Follow me for similar post : 🇮🇳 Ashish Patel Interesting Facts : 🔸 It is published in 2017 ICCV with more than 660 citations. 🔸Fully Convolutional Instance-aware Semantic Segmentation, with Position-Sensitive Inside/Outside Score Maps ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eNiPGWY Code : https://lnkd.in/etsK8bM ------------------------------------------------------ ------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 FCIS won the 1st place in 2016 COCO segmentation challenge, outperform the second place entry by 12% in accuracy relatively. It also ranked 2nd in 2016 COCO detection leaderboard at that moment. It was named as Translation-aware Fully Convolutional Instance Segmentation (TA-FCN) initially. 🔸FCIS only takes 0.24s per image using ResNet-101 (Nvidia K40) which is much faster than that of MNC. #computervision #artificialintelligence #data