BAM: A Lightweight and Efficient Balanced Attention Mechanism for Single Image Super Resolution

by   Fanyi Wang, et al.

Single image super-resolution (SISR) is one of the most challenging problems in the field of computer vision. Among the deep convolutional neural network based methods, attention mechanism has shown the enormous potential. However, due to the diverse network architectures, there is a lack of a universal attention mechanism for the SISR task. In this paper, we propose a lightweight and efficient Balanced Attention Mechanism (BAM), which can be generally applicable for different SISR networks. It consists of Avgpool Channel Attention Module (ACAM) and Maxpool Spatial Attention Module (MSAM). These two modules are connected in parallel to minimize the error accumulation and the crosstalk. To reduce the undesirable effect of redundant information on the attention generation, we only apply Avgpool for channel attention because Maxpool could pick up the illusive extreme points in the feature map across the spatial dimensions, and we only apply Maxpool for spatial attention because the useful features along the channel dimension usually exist in the form of maximum values for SISR task. To verify the efficiency and robustness of BAM, we apply it to 12 state-of-the-art SISR networks, among which eight were without attention thus we plug BAM in and four were with attention thus we replace its original attention module with BAM. We experiment on Set5, Set14 and BSD100 benchmark datasets with the scale factor of x2 , x3 and x4 . The results demonstrate that BAM can generally improve the network performance. Moreover, we conduct the ablation experiments to prove the minimalism of BAM. Our results show that the parallel structure of BAM can better balance channel and spatial attentions, thus outperforming the series structure of prior Convolutional Block Attention Module (CBAM).


page 10

page 12

page 13


GDCA: GAN-based single image super resolution with Dual discriminators and Channel Attention

Single Image Super-Resolution (SISR) is a very active research field. Th...

An attention mechanism based convolutional network for satellite precipitation downscaling over China

Precipitation is a key part of hydrological circulation and is a sensiti...

Convolutional Neural Network with Convolutional Block Attention Module for Finger Vein Recognition

Convolutional neural networks have become a popular research in the fiel...

Parameter-Free Channel Attention for Image Classification and Super-Resolution

The channel attention mechanism is a useful technique widely employed in...

Lightweight Spatial-Channel Adaptive Coordination of Multilevel Refinement Enhancement Network for Image Reconstruction

Benefiting from the vigorous development of deep learning, many CNN-base...

G-DARTS-A: Groups of Channel Parallel Sampling with Attention

Differentiable Architecture Search (DARTS) provides a baseline for searc...

IMDeception: Grouped Information Distilling Super-Resolution Network

Single-Image-Super-Resolution (SISR) is a classical computer vision prob...

Please sign up or login with your details

Forgot password? Click here to reset