𝗗𝗮𝘆-𝟭𝟯𝟱 Computer Vision Learning Learning Saliency Propagation for Semi-Supervised Instance Segmentation by UC Berkeley Follow me for similar post : 🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in CVPR 2020 with over 6 citations. 🔸 It Outperforms with RetinaMask, Mask-RCNN etc. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/ehE_KcB Code : https://lnkd.in/eZmMHcx ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 ShapeProp jointly learns from the abundant yet coarse-grained boxes and the fine-detailed yet limited amount of masks to extract a shape representation, which provide strong shape prior to mask head to improve segmentation accuracy and generalization. #computervision #artificialintelligence #machinelearning
LINE5•2K followers
4ySounds like a winner! Im always wxcited about object detection stuff, in my experience its the most challenging of the basic CV tasks.