A Comparative Analysis of Single-Stage Detectors from the Perspectives of Anchor-Free and Anchor-Based Approaches

Peigeng Li

doi:10.54097/s37sgq58

Authors

Peigeng Li

DOI:

https://doi.org/10.54097/s37sgq58

Keywords:

Anchor-free, anchor based, one-stage detector.

Abstract

Since the emergence of deep learning in object detection in 2014, there has been rapid development and widespread application of detectors across various domains such as healthcare, road traffic, and industrial inspection. The evolution of convolutional neural network (CNN)-based detectors has reached a mature stage, with single-stage detectors playing a crucial role within CNN-based frameworks. This paper provides an analysis of the developmental process and distinctive features of classic single-stage detectors categorized into two types: Anchor-free and Anchor-based. Furthermore, the paper also provides a comparison of the accuracy trends for these two types of single-stage detectors over different years. Through this analysis and comparison, potential reasons behind the advancements in single-stage detectors during different time periods can be explored, such as network architecture optimization, increase in datasets, and algorithm improvements. Additionally, this paper offers insights into current research focal points and future prospects.

Downloads

Download data is not yet available.

References

J. Redmon, S. Divvala, R. Girshick, A. Farhadi. You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016, 91, 779 - 788.

Juan Terven, Diana Cordova-Esparza. A Comprehensive Review of YOLO: From YOLOv1 and Beyond. 2023 arXiv, 2304.00501.

Hei Law, Jia Deng. CornerNet: Detecting Objects as Paired Keypoints. 2019, arXiv, 1808.01244.

Kaiwen Duan, Song Bai, Lingxi Xie, Honggang Qi, Qingming Huang, Qi Tian. (2019). CenterNet: Keypoint Triplets for Object Detection. arXiv, 1904.08189. Retireved Augst 20, 2023.

Xingyi Zhou, Dequan Wang, Philipp Krähenbühl. Objects as Points. 2019, arXiv, 1904.07850.

Zhi Tian, Chunhua Shen, Hao Chen, Tong He. FCOS: Fully Convolutional One-Stage Object Detection. 2019, arXiv, 1904.01355.

Zhi Tian, Chunhua Shen, Hao Chen, Tong He. FCOS: A simple and strong anchor-free object detector. 2020 arXiv, 2006.09214.

J Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Berg. SSD: Single Shot MultiBox Detector. Computer Vision 2016, 21 - 37.

Joseph Redmon, Ali Farhadi. YOLO9000: Better, Faster, Stronger.2019 arXiv, 1612.08242.

Tsung-Yi Lin, Priya Goyal, Ross Girshick,, Kaiming He, Piotr Dollár. Focal Loss for Dense Object Detection.2018 arXiv, 1708.02002.

Everingham, M., Van~Gool, L., Williams, C. K. I., Winn, J., Zisserman. The Pascal Visual Object Classes (VOC) Challenge. International Journal of Computer Vision. 2010, 88, 303 - 338.

Tsung-Yi Lin, Michael Maire, Serge Belongie, Lubomir Bourdev, Ross Girshick, James Hays, Pietro Perona, Deva Ramanan, C. Lawrence Zitnick, Piotr Dollár. Microsoft COCO: Common Objects in Context.2015 arXiv, 1405.0312.

Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie. (2017). Feature Pyramid Networks for Object Detection. 2017 arXiv, 1612.03144.