Neural Architecture Search for Dense Prediction Tasks in Computer Vision
This is an incremental survey paper that helps researchers and practitioners in computer vision by summarizing existing NAS methods for dense prediction tasks.
The paper provides an overview of neural architecture search (NAS) for dense prediction tasks in computer vision, such as semantic segmentation and object detection, by addressing challenges like high memory usage and complex architectures to facilitate future research and application.
The success of deep learning in recent years has lead to a rising demand for neural network architecture engineering. As a consequence, neural architecture search (NAS), which aims at automatically designing neural network architectures in a data-driven manner rather than manually, has evolved as a popular field of research. With the advent of weight sharing strategies across architectures, NAS has become applicable to a much wider range of problems. In particular, there are now many publications for dense prediction tasks in computer vision that require pixel-level predictions, such as semantic segmentation or object detection. These tasks come with novel challenges, such as higher memory footprints due to high-resolution data, learning multi-scale representations, longer training times, and more complex and larger neural architectures. In this manuscript, we provide an overview of NAS for dense prediction tasks by elaborating on these novel challenges and surveying ways to address them to ease future research and application of existing methods to novel problems.