Pyramidal Dense Attention Networks for Lightweight Image Super-Resolution
This work addresses the challenge of deploying super-resolution models on embedded devices, representing an incremental improvement in lightweight architectures.
The paper tackles the problem of high memory cost in deep convolutional neural networks for image super-resolution, proposing a pyramidal dense attention network (PDAN) that achieves superior performance compared to state-of-the-art lightweight methods.
Recently, deep convolutional neural network methods have achieved an excellent performance in image superresolution (SR), but they can not be easily applied to embedded devices due to large memory cost. To solve this problem, we propose a pyramidal dense attention network (PDAN) for lightweight image super-resolution in this paper. In our method, the proposed pyramidal dense learning can gradually increase the width of the densely connected layer inside a pyramidal dense block to extract deep features efficiently. Meanwhile, the adaptive group convolution that the number of groups grows linearly with dense convolutional layers is introduced to relieve the parameter explosion. Besides, we also present a novel joint attention to capture cross-dimension interaction between the spatial dimensions and channel dimension in an efficient way for providing rich discriminative feature representations. Extensive experimental results show that our method achieves superior performance in comparison with the state-of-the-art lightweight SR methods.