Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟯𝟮𝟮 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵𝗲𝗿𝘀 𝗵𝗮𝘀 𝗽𝘂𝗯𝗹𝗶𝘀𝗵𝗲𝗱 𝗜𝗺𝗮𝗴𝗲-𝘀𝗽𝗲𝗰𝗶𝗳𝗶𝗰 𝗖𝗼𝗻𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻𝗮𝗹 𝗞𝗲𝗿𝗻𝗲𝗹 𝗠𝗼𝗱𝘂𝗹𝗮𝘁𝗶𝗼𝗻 𝗳𝗼𝗿 𝗦𝗶𝗻𝗴𝗹𝗲 𝗜𝗺𝗮𝗴𝗲 𝗦𝘂𝗽𝗲𝗿-𝗿𝗲𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻 Follow me for a similar post: 🇮🇳 Ashish Patel ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 Paper: 𝗜𝗺𝗮𝗴𝗲-𝘀𝗽𝗲𝗰𝗶𝗳𝗶𝗰 𝗖𝗼𝗻𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻𝗮𝗹 𝗞𝗲𝗿𝗻𝗲𝗹 𝗠𝗼𝗱𝘂𝗹𝗮𝘁𝗶𝗼𝗻 𝗳𝗼𝗿 𝗦𝗶𝗻𝗴𝗹𝗲 𝗜𝗺𝗮𝗴𝗲 𝗦𝘂𝗽𝗲𝗿-𝗿𝗲𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻 🔸 This paper is published in IEEE Transactions in 2021. 🔸 Single image super-resolution (SR) aims at reconstructing a high-resolution (HR) image from a single low-resolution (LR) image obtained by limited imaging devices, which is considered as a challenging ill-posed inverse problem and widely used in computer vision applications where high-frequency details are greatly desired, such as medical imaging, security, and surveillance. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Recently, deep-learning-based super-resolution methods have achieved excellent performances, but mainly focus on training a single generalized deep network by feeding numerous samples. Yet intuitively, each image has its representation and is expected to acquire an adaptive model.  🔸 For this issue, we propose a novel image-specific convolutional kernel modulation (IKM) by exploiting the global contextual information of image or feature to generate an attention weight for adaptively modulating the convolutional kernels, which outperforms the vanilla convolution and several existing attention mechanisms while embedding into the state-of-the-art architectures without any additional parameters.  🔸 Particularly, to optimize our IKM in mini-batch training, we introduce an image-specific optimization (IsO) algorithm, which is more effective than the conventional mini-batch SGD optimization.  🔸 Furthermore, we investigate the effect of IKM on the state of-the-art architectures and exploit a new backbone with U-style residual learning and hourglass dense block learning, terms U-Hourglass Dense Network (U-HDN), which is an appropriate architecture to utmost improve the effectiveness of IKM theoretically and experimentally. Extensive experiments on single image super-resolution show that the proposed methods achieve superior performances over state-of-the-art methods. #computervision #artificialintelligence #innovation