Single Image Super-Resolution Using Inverted Residual and Channel-Wise Attention

Single-image super-resolution (SISR) is the task of reconstructing a high-resolution image from a low-resolution image. Convolutional neural network (CNN)-based SISR techniques have demonstrated promising results. However, most CNN-based models cannot discriminate between different forms of information and treat them identically, which limits the models' ability to represent information. On the other hand, when a neural network's depth increases, the long-term information from earlier layers is more likely to degrade in later levels, which leads to poor image SR performance. This research presents a single image super-resolution strategy employing inverted residual connection with channel-wise attention (IRCA) to preserve meaningful information and keep long-term features while balancing performance and computational cost. The inverted residual block achieves long-term information persistence with fewer parameters than traditional residual networks. Meanwhile, by explicitly modeling inter-dependencies between channels, the attention block progressively adjusts channel-wise feature responses, enhancing essential information and suppressing unnecessary information. The efficacy of our suggested approach is demonstrated in three publicly accessible datasets. Code is available at https://github.com/mdhosen/SISR_IResBlock