Lightweight Asymmetric Convolutional Distillation Network for Single Image Super-Resolution
Jun Wu, Yuxi Wang, Xuguang Zhang
Abstract
Recent single image super-resolution methods based on various complex deep neural networks have achieved remarkable success. However, these methods require a large amount of computational overhead while improving performance, and thus are difficult to apply to mobile devices in real-world scenarios. In this letter, we design an efficient asymmetric convolutional distillation block (ACDB). Especially in this block, introducing an asymmetric convolution block (ACB) and reusing shallow distillation features can effectively improve the performance of the model and reduce the model complexity. Our model achieves efficient performance while maintaining low complexity.>
Topics & Concepts
Computer scienceBlock (permutation group theory)Convolutional neural networkConvolution (computer science)DistillationReuseOverhead (engineering)Computational complexity theoryImage (mathematics)Resolution (logic)Computer engineeringArtificial intelligenceAlgorithmArtificial neural networkMathematicsEngineeringWaste managementOrganic chemistryOperating systemGeometryChemistryAdvanced Image Processing TechniquesAdvanced Vision and ImagingImage Processing Techniques and Applications