Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟮𝟰𝟮 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗢𝗿𝗶𝗲𝗻𝘁𝗲𝗱 𝗥-𝗖𝗡𝗡 𝗳𝗼𝗿 𝗢𝗯𝗷𝗲𝗰𝘁 𝗗𝗲𝘁𝗲𝗰𝘁𝗶𝗼𝗻 𝗯𝘆 𝗡𝗼𝗿𝘁𝗵𝘄𝗲𝘀𝘁𝗲𝗿𝗻 𝗣𝗹𝗼𝘆𝘁𝗲𝗰𝗵𝗻𝗶𝗰𝗮𝗹 𝗨𝗻𝗶𝘃𝗲𝗿𝘀𝗶𝘁𝘆, 𝗫𝗶’𝗮𝗻, 𝗖𝗵𝗶𝗻𝗮 Follow me for a similar post: 🇮🇳 Ashish Patel Interesting Facts : 🔸 This paper is published ICCV2021. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eptJMdu8 Code: https://lnkd.in/eCRFmm29 ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Current state-of-the-art two-stage detectors generate oriented proposals through time-consuming schemes. This diminishes the detectors' speed, thereby becoming the computational bottleneck in advanced oriented object detection systems.  🔸 This work proposes an effective and simple oriented object detection framework, termed Oriented R-CNN, which is a general two-stage oriented detector with promising accuracy and efficiency.  🔸 To be specific, in the first stage, we propose an oriented Region Proposal Network (oriented RPN) that directly generates high-quality oriented proposals in a nearly cost-free manner. The second stage is oriented R-CNN head for refining oriented Regions of Interest (oriented RoIs) and recognizing them.  🔸 Without tricks, oriented R-CNN with ResNet50 achieves state-of-the-art detection accuracy on two commonly-used datasets for oriented object detection including DOTA (75.87% mAP) and HRSC2016 (96.50% mAP), while having a speed of 15.1 FPS with the image size of 1024×1024 on a single RTX 2080Ti. We hope our work could inspire rethinking the design of oriented detectors and serve as a baseline for oriented object detection. #computervision #artificialintelligence #machinelearning