PAMS: Quantized Super-Resolution via Parameterized Max Scale
european conference on computer vision, pp. 564-580, 2020.
Deep convolutional neural networks (DCNNs) have shown dominant performance in the task of super-resolution (SR). However, their heavy memory cost and computation overhead significantly restrict their practical deployments on resource-limited devices, which mainly arise from the floating-point storage and operations between weights and a...More
PPT (Upload PPT)