Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟭𝟳𝟰 Computer Vision Learning 𝗦𝗶𝗽𝗠𝗮𝘀𝗸: Spatial Information Preservation for Fast Image and Video Instance Segmentation by Zayed University of Artificial Intelligence, UAE Follow me for similar post:  🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in ECCV2020 with over 9 citations. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/e9wXqNs Code : https://lnkd.in/epiH2ei ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Single-stage instance segmentation approaches have recently gained popularity due to their speed and simplicity, but are still lagging behind in accuracy, compared to two-stage methods.  🔸 Fast single-stage instance segmentation method, called SipMask, that preserves instance-specific spatial information by separating mask prediction of an instance to different sub-regions of a detected bounding-box. Main contribution is a novel light-weight spatial preservation (SP) module that generates a separate set of spatial coefficients for each sub-region within a bounding-box, leading to improved mask predictions. It also enables accurate delineation of spatially adjacent instances.  🔸Introduce a mask alignment weighting loss and a feature alignment scheme to better correlate mask prediction with object detection. #computervision #artificialintelligence #data