Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟭𝟵𝟲 Computer Vision Learning Image Super-Resolution with 𝗡𝗼𝗻-𝗟𝗼𝗰𝗮𝗹 𝗦𝗽𝗮𝗿𝘀𝗲 𝗔𝘁𝘁𝗲𝗻𝘁𝗶𝗼𝗻 𝗯𝘆 𝗨𝗻𝗶𝘃𝗲𝗿𝘀𝗶𝘁𝘆 𝗼𝗳 𝗜𝗹𝗹𝗶𝗻𝗼𝗶𝘀 𝗮𝘁 𝗨𝗿𝗯𝗮𝗻𝗮-𝗖𝗵𝗮𝗺𝗽𝗮𝗶𝗴𝗻 Follow me for a similar post:  🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in CVPR2021 with over 2 citations. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/exTAFvn Code: https://lnkd.in/exRAYHA ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Both Non-Local (NL) operation and sparse representation are crucial for Single Image Super-Resolution (SISR).In this paper, we investigate their combinations and propose a novel Non-Local Sparse Attention (NLSA) with a dynamic sparse attention pattern.  🔸 NLSA is designed to retain long-range modeling capability from NL operation while enjoying robustness and high efficiency of sparse representation. Specifically, NLSA rectifies non-local attention with spherical locality sensitive hashing (LSH) that partitions the input space into hash buckets of related features.  🔸  For every query signal, NLSA assigns a bucket to it and only computes attention within the bucket. The resulting sparse attention prevents the model from attending to locations that are noisy and less informative while reducing the computational cost from quadratic to asymptotic linear with respect to the spatial size.  🔸 Extensive experiments validate the effectiveness and efficiency of NLSA. With a few non-local sparse attention modules, our architecture, called non-local sparse network (NLSN), reaches state-of-the-art performance for SISR quantitatively and qualitatively. #computervision #artificialintelligence #deeplearning