Day-15 Computer Vision Learning R-FCN — Positive-Sensitive Score Maps (Object Detection) by Microsoft and Tsinghua University 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀: ♦ This is a paper in 2016 NIPS with more than 700 citations. --------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://bit.ly/35DTZ4I 𝗣𝘆𝘁𝗼𝗿𝗰𝗵: https://bit.ly/39xN9if 𝗧𝗲𝗻𝘀𝗼𝗿𝗳𝗹𝗼𝘄𝟮: https://bit.ly/3bAzHwS 𝗞𝗲𝗿𝗮𝘀: https://bit.ly/3qrrQpD ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 ♦ For traditional region proposal network (RPN) approaches such as R-CNN, Fast R-CNN and Faster R-CNN, region proposals are generated by RPN first. Then ROI pooling is done, and going through fully connected (FC) layers for classification and bounding box regression. ♦ The process (FC layers) after ROI pooling does not share among ROI, and takes time, which makes RPN approaches slow. And the FC layers increase the number of connections (parameters) which also increase the complexity. Note : More in Comments #innovation #artificialintelligence #computervision
Sign in to view more content
Create your free account or sign in to continue your search
or
New to LinkedIn? Join now
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲 𝗼𝗳 𝗥-𝗙𝗖𝗡 ♦ In R-FCN, we still have RPN to obtain region proposals, but unlike R-CNN series, FC layers after ROI pooling are removed. Instead, all major complexity is moved before ROI pooling to generate the score maps. ♦ All region proposals, after ROI pooling, will make use of the same set of score maps to perform average voting, which is a simple calculation. Thus, No learnable layer after ROI layer which is nearly cost-free. As a results, R-FCN is even faster than Faster R-CNN with competitive mAP.