Ashish Patel 🇮🇳’s Post

Day-63 Computer Vision Learning Light-Head R-CNN — In Defense of Two-Stage Object Detector (Object Detection) by Tsinghua University, and MEGVII旷视 Follow me for similar post : 🇮🇳 Ashish Patel Interesting Facts : 🔸 It is published in 2017 arxiv, which has already got over 177 citations. 🔸 It outperforms R-FCN, Faster R-CNN, DCNv1, G-RMI, FPN, Mask R-CNN, RetinaNet, YOLOv2 &SSD. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/ev8kVGW Official Code : https://bit.ly/2OkpafB tensorflow : https://bit.ly/30f9X2d pytorch : https://bit.ly/3kI8bjD keras : https://bit.ly/30f9X2d ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 A light-head R-CNN is introduced to speed up the inference. 🔸 Faster R-CNN adopts a powerful R-CNN which utilizes two large fully connected layers or whole ResNet stage 5 as a second stage classifier. 🔸 However, the computation could be intensive especially when the number of object proposals is large. #computervision #arttificialintelligence #innovation