A Cosine Network for Image Super-Resolution

TL;DR

This paper introduces CSRNet, a novel deep learning architecture for image super-resolution that leverages heterogeneous blocks and cosine annealing to improve structural information extraction and training efficiency.

Contribution

The paper proposes a new network architecture with heterogeneous blocks and a cosine annealing training strategy for enhanced image super-resolution performance.

Findings

CSRNet achieves competitive results with state-of-the-art methods.

The use of heterogeneous blocks improves structural information extraction.

Cosine annealing enhances training stability and convergence.

Abstract

Deep convolutional neural networks can use hierarchical information to progressively extract structural information to recover high-quality images. However, preserving the effectiveness of the obtained structural information is important in image super-resolution. In this paper, we propose a cosine network for image super-resolution (CSRNet) by improving a network architecture and optimizing the training strategy. To extract complementary homologous structural information, odd and even heterogeneous blocks are designed to enlarge the architectural differences and improve the performance of image super-resolution. Combining linear and non-linear structural information can overcome the drawback of homologous information and enhance the robustness of the obtained structural information in image super-resolution. Taking into account the local minimum of gradient descent, a cosine annealing mechanism is used to optimize the training procedure by performing warm restarts and adjusting the learning rate. Experimental results illustrate that the proposed CSRNet is competitive with state-of-the-art methods in image super-resolution.