DLAFS CASCADE R-CNN: AN OBJECT DETECTOR BASED ON DYNAMIC LABEL ASSIGNMENT

Authors

  • Doanh Bui Cao University of Information Technology, VNU-HCM, Viet Nam
  • Nguyen Vo Duy University of Information Technology, VNU-HCM, Viet Nam
  • Khang Nguyen University of Information Technology, VNU-HCM, Viet Nam

DOI:

https://doi.org/10.15625/1813-9663/38/2/16252

Keywords:

Object detection, Marine vehicle, Cascade R-CNN, Document detection.

Abstract

Object detection methods based on Deep Learning are the revolution of the Computer Vision field in general and object detection problems in particular. In detail, they are methods that belonged to the R - CNN family: Faster R - CNN and Cascade R - CNN. The characteristic of them is the Region Proposal Network, which is utilized for generating proposal regions that may include objects or not, then the proposals will be classified by the IoU threshold. In this study, we apply dynamic training, which adjusts this IoU threshold depending on the statistic of proposal regions on the Faster R - CNN and Cascade R - CNN, training on the SeaShips and DODV dataset. Cascade R - CNN with dynamic training achieve higher results compared to normal on both two datasets (higher 0.2% and 5.7% on the SeaShips and DODV dataset, respectively). In the DODV dataset, Faster R - CNN with dynamic training also perform higher results compared to its normal version, 4.4% higher.

Metrics

Metrics Loading ...

Downloads

Published

2022-06-23

How to Cite

[1]
D. Bui Cao, N. Vo Duy, and K. Nguyen, “DLAFS CASCADE R-CNN: AN OBJECT DETECTOR BASED ON DYNAMIC LABEL ASSIGNMENT”, JCC, vol. 38, no. 2, p. 131–145, Jun. 2022.

Issue

Section

Articles