Ashish Patel 🇮🇳’s Post

Day-56 Computer Vision Learning SSD — Single Shot Detector (Object Detection) by University of Michigan Follow me for similar post : 🇮🇳 Ashish Patel Interesting Facts : 🔸 It is published in 2016 ECCV, which has already got over 13068 citations. 🔸 By using SSD, we only need to take one single shot to detect multiple objects within the image, while regional proposal network (RPN) based approaches such as R-CNN series that need two shots, one for generating region proposals, one for detecting the object of each proposal. Thus, SSD is much faster compared with two-shot RPN-based approaches. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eknTfCK official code : https://bit.ly/3dHNQcF Tensorflow : https://bit.ly/2NUCfvX pytorch :https://bit.ly/2ZP6uXV keras: https://bit.ly/2ZNW8ay ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 SSD300 achieves 74.3% mAP at 59 FPS while SSD500 achieves 76.9% mAP at 22 FPS, which outperforms Faster R-CNN (73.2% mAP at 7 FPS) and YOLOv1 (63.4% mAP at 45 FPS). #computervision #artificialintelligence #innovation