“Efficient image super-resolution (SR) has witnessed rapid progress thanks to novel lightweight architectures or model compression techniques (e.g., neural architecture search and knowledge distillation). Nevertheless, these methods consume considerable resources or/and neglect to squeeze out the network redundancy at a more fine-grained convolution filter level. … Structured pruning is known to be tricky when applied to SR networks because the extensive residual blocks demand the pruned indices of different layers to be the same. … In this article, we present Global Aligned Structured Sparsity Learning (GASSL) to resolve these problems.”

Find the paper and full list of authors at IEEE Xplore.