Neural architecture search: A contemporary literature review for computer vision applications

Poyser, Matt; Breckon, Toby P.

Abstract

Deep Neural Networks have received considerable attention in recent years. As the complexity of network architecture increases in relation to the task complexity, it becomes harder to manually craft an optimal neural network architecture and train it to convergence. As such, Neural Architecture Search (NAS) is becoming far more prevalent within computer vision research, especially when the construction of efficient, smaller network architectures is becoming an increasingly important area of research, for which NAS is well suited. However, despite their promise, contemporary and end-to-end NAS pipeline require vast computational training resources. In this paper, we present a comprehensive overview of contemporary NAS approaches with respect to image classification, object detection, and image segmentation. We adopt consistent terminology to overcome contradictions common within existing NAS literature. Furthermore, we identify and compare current performance limitations in addition to highlighting directions for future NAS research.

Citation

Poyser, M., & Breckon, T. P. (2024). Neural architecture search: A contemporary literature review for computer vision applications. Pattern Recognition, 147, 110052. https://doi.org/10.1016/j.patcog.2023.110052

• Journal Article Type: Article
• Acceptance Date: Oct 13, 2023
• Online Publication Date: Oct 24, 2023
• Publication Date: 2024-03
• Deposit Date: Nov 2, 2023
• Publicly Available Date: Nov 2, 2023
• Journal: Pattern Recognition
• Print ISSN: 0031-3203
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 147
• Pages: 110052
• DOI: https://doi.org/10.1016/j.patcog.2023.110052
• Keywords: Artificial Intelligence; Computer Vision and Pattern Recognition; Signal Processing; Software
• Public URL: https://durham-repository.worktribe.com/output/1874778