Timezone: »

ShuffleMixer: An Efficient ConvNet for Image Super-Resolution
Long Sun · Jinshan Pan · Jinhui Tang

Tue Nov 29 09:00 AM -- 11:00 AM (PST) @ Hall J #216
Lightweight and efficiency are critical drivers for the practical application of image super-resolution (SR) algorithms. We propose a simple and effective approach, ShuffleMixer, for lightweight image super-resolution that explores large convolution and channel split-shuffle operation. In contrast to previous SR models that simply stack multiple small kernel convolutions or complex operators to learn representations, we explore a large kernel ConvNet for mobile-friendly SR design. Specifically, we develop a large depth-wise convolution and two projection layers based on channel splitting and shuffling as the basic component to mix features efficiently. Since the contexts of natural images are strongly locally correlated, using large depth-wise convolutions only is insufficient to reconstruct fine details. To overcome this problem while maintaining the efficiency of the proposed module, we introduce Fused-MBConvs into the proposed network to model the local connectivity of different features. Experimental results demonstrate that the proposed ShuffleMixer is about $3 \times$ smaller than the state-of-the-art efficient SR methods, e.g. CARN, in terms of model parameters and FLOPs while achieving competitive performance.

Author Information

Long Sun (Nanjing University of Science and Technology)
Jinshan Pan (Nanjing University of Science and Technology)
Jinhui Tang (Nanjing University of Science and Technology)

More from the Same Authors