HASN: Hybrid Attention Separable Network for Efficient Image Super-resolution

TL;DR

HASN introduces a lightweight, efficient image super-resolution network that combines hybrid attention mechanisms with depthwise separable convolutions, achieving high performance with fewer parameters and lower computational costs.

Contribution

The paper proposes the Hybrid Attention Separable Block (HASB) and a warm-start retraining strategy to improve super-resolution efficiency and effectiveness.

Findings

Achieves high super-resolution performance with fewer parameters.

Reduces computational complexity compared to existing methods.

Maintains strong feature extraction capabilities with lightweight design.

Abstract

Recently, lightweight methods for single image super-resolution (SISR) have gained significant popularity and achieved impressive performance due to limited hardware resources. These methods demonstrate that adopting residual feature distillation is an effective way to enhance performance. However, we find that using residual connections after each block increases the model's storage and computational cost. Therefore, to simplify the network structure and learn higher-level features and relationships between features, we use depthwise separable convolutions, fully connected layers, and activation functions as the basic feature extraction modules. This significantly reduces computational load and the number of parameters while maintaining strong feature extraction capabilities. To further enhance model performance, we propose the Hybrid Attention Separable Block (HASB), which combines channel attention and spatial attention, thus making use of their complementary advantages. Additionally, we use depthwise separable convolutions instead of standard convolutions, significantly reducing the computational load and the number of parameters while maintaining strong feature extraction capabilities. During the training phase, we also adopt a warm-start retraining strategy to exploit the potential of the model further. Extensive experiments demonstrate the effectiveness of our approach. Our method achieves a smaller model size and reduced computational complexity without compromising performance. Code can be available at https://github.com/nathan66666/HASN.git