Lightweight Residual Balanced Distillation Network for Image Super-Resolution
The existing single image super-resolution reconstruction techniques using convo-lutional neural networks generally have the problem of large number of parameters and high calculation cost,which hinders the application of practical scenarios.Therefore,a light-weight blueprint separable residual balanced distillation network(BSRBDN)is proposed.Firstly,blueprint separable convolution is introduced and a multi-scale progressive feature distillation connection structure is proposed to reduce redundant operations while extracting deep features.Secondly,contrast balanced attention block,large kernel space attention block and pixel fusion module are designed to activate high-frequency information to enhance edge detail features.Finally,a lightweight blueprint separable residual balanced distillation network is designed to accomplish image reconstruction quickly and accurately.Experimen-tal results show that the network greatly reduces the parameters and computation while maintaining better performance and subjective visualization.
万方数据
维普
