Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟭𝟰𝟴 Computer Vision Learning 𝗔𝘁𝘁𝗲𝗻𝘁𝗶𝗼𝗻-𝗥𝗣𝗡: Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector by Tencent Follow me for a similar post:  🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in CVPR 2020 with over 74 citations. 🔸 It Outperforms with RetinaNet, RepPoints, CenterNet, CornetNet-lite, CornetNet, Grid R-CNN, ExtreameNet etc. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/e-8VuVM Proposed dataset: https://lnkd.in/ejA9UQP code: https://lnkd.in/eQRtbvu ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Traditional target detection methods usually require a large amount of training data, and preparing such high-quality training data has a great labor cost.  🔸 In this paper, the authors have proposed the new method Attention-RPN that contains Multi-Relation Detector and Contrastive Training strategy, which uses the similarity between the Few-Shot support set and the query set to detect new targets, while suppressing the background False detection. 🔸 This paper is also proposed the new dataset which contains 1000 objects of the different categories with high-quality annotations.  #computervision #artificialintelligence