Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟭𝟱𝟮 Computer Vision Learning 𝗖𝗲𝗻𝘁𝗿𝗶𝗽𝗲𝘁𝗮𝗹𝗡𝗲𝘁:: Pursuing High-quality Keypoint Pairs for Object Detection by SenseTime Research Follow me for similar post :  🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in CVPR 2020 with over 31 citations. 🔸 It Outperforms with the Extreme Net, CornerNet, FCOS, RPDet etc. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/evscDUK code : https://lnkd.in/eTgWsK4 ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Keypoint-based detectors have achieved pretty-well performance. However, incorrect keypoint matching is still widespread and greatly affects the performance of the detector. 🔸 CentripetalNet which uses centripetal shift to pair corner keypoints from the same instance. CentripetalNet predicts the position and the centripetal shift of the corner points and matches corners whose shifted results are aligned.Combining position information, our approach matches corner points more accurately than the conventional embedding approaches do. Corner pooling extracts information inside the bounding boxes onto the border. #computervision #artificialintelligence #data