Efficient Residual Dense Block Search for Image Super-Resolution

25 Sep 2019  ·  Dehua Song, Chang Xu, Xu Jia, Yiyi Chen, Chunjing Xu, Yunhe Wang ·

Although remarkable progress has been made on single image super-resolution due to the revival of deep convolutional neural networks, deep learning methods are confronted with the challenges of computation and memory consumption in practice, especially for mobile devices. Focusing on this issue, we propose an efficient residual dense block search algorithm with multiple objectives to hunt for fast, lightweight and accurate networks for image super-resolution. Firstly, to accelerate super-resolution network, we exploit the variation of feature scale adequately with the proposed efficient residual dense blocks. In the proposed evolutionary algorithm, the locations of pooling and upsampling operator are searched automatically. Secondly, network architecture is evolved with the guidance of block credits to acquire accurate super-resolution network. The block credit reflects the effect of current block and is earned during model evaluation process. It guides the evolution by weighing the sampling probability of mutation to favor admirable blocks. Extensive experimental results demonstrate the effectiveness of the proposed searching method and the found efficient super-resolution models achieve better performance than the state-of-the-art methods with limited number of parameters and FLOPs.

PDF Abstract


  Add Datasets introduced or used in this paper

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.