Neural Architecture Search for Image Super-Resolution Using Densely Constructed Search Space: DeCoNAS
This work addresses the challenge of automating network design for image super-resolution, which is important for applications like image enhancement, but it is incremental as it builds on existing NAS methods.
The authors tackled the problem of finding optimal neural network structures for single image super-resolution by expanding neural architecture search (NAS) to this domain, resulting in DeCoNASNet, a lightweight densely connected network that outperforms state-of-the-art lightweight super-resolution networks designed by handcraft methods and existing NAS-based designs.
The recent progress of deep convolutional neural networks has enabled great success in single image super-resolution (SISR) and many other vision tasks. Their performances are also being increased by deepening the networks and developing more sophisticated network structures. However, finding an optimal structure for the given problem is a difficult task, even for human experts. For this reason, neural architecture search (NAS) methods have been introduced, which automate the procedure of constructing the structures. In this paper, we expand the NAS to the super-resolution domain and find a lightweight densely connected network named DeCoNASNet. We use a hierarchical search strategy to find the best connection with local and global features. In this process, we define a complexity-based penalty for solving image super-resolution, which can be considered a multi-objective problem. Experiments show that our DeCoNASNet outperforms the state-of-the-art lightweight super-resolution networks designed by handcraft methods and existing NAS-based design.