A survey of modern deep learning based object detection models
Syed Sahil Abbas Zaidia✉, Mohd. Samar Ansarib, Asra Aslamc, Nadia Kanwald e, Mamoona Naveed Asgharf, Brian Leea
- aSoftware Research Institute, Technological University of the Shannon: Midlands Midwest, Athlone, N37 HD68, Westmeath, Ireland
- bFaculty of Science and Engineering, University of Chester, United Kingdom
- cInsight Centre for Data Analytics, National University of Ireland, Galway, Ireland
- dLahore College for Women University, Pakistan
- eSchool of Computing and Mathematics, Keele University, United Kingdom
- fSchool of Computer Science, National University of Ireland, Galway, Ireland
- ✉Corresponding author
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
Object Detection is the task of classification and localization of objects in an image or video. It has gained prominence in recent years due to its widespread applications. This article surveys recent developments in deep learning based object detectors. Concise overview of benchmark datasets and evaluation metrics used in detection is also provided along with some of the prominent backbone architectures used in recognition tasks. It also covers contemporary lightweight classification models used on edge devices. Lastly, we compare the performances of these architectures on multiple metrics.
TL;DRRecent developments in deep learning based object detectors are surveyed along with some of the prominent backbone architectures used in recognition tasks. (Semantic Scholar)