Classic versus deep learning approaches to address computer vision challenges
This work provides a comparative analysis for researchers and practitioners in computer vision, highlighting trade-offs to guide method selection, but it is incremental as it synthesizes existing knowledge without introducing new techniques.
The study compared classic and deep learning approaches for computer vision tasks, specifically faint edge detection and multispectral image registration, finding that deep learning methods outperform in accuracy and development time but require more resources and lack generalizability outside training data.
Computer vision and image processing address many challenging applications. While the last decade has seen deep neural network architectures revolutionizing those fields, early methods relied on 'classic', i.e., non-learned approaches. In this study, we explore the differences between classic and deep learning (DL) algorithms to gain new insight regarding which is more suitable for a given application. The focus is on two challenging ill-posed problems, namely faint edge detection and multispectral image registration, studying recent state-of-the-art DL and classic solutions. While those DL algorithms outperform classic methods in terms of accuracy and development time, they tend to have higher resource requirements and are unable to perform outside their training space. Moreover, classic algorithms are more transparent, which facilitates their adoption for real-life applications. As both classes of approaches have unique strengths and limitations, the choice of a solution is clearly application dependent.