Acceso abierto

Object Localization Algorithm Based on Meta-Reinforcement Learning

Han Yan

Han Yan

Xi’an Technological University, School of Computer Science & EngineeringXi’an, China
Buscar este autor en
Sciendo|Google Scholar
Yan, Han
 y 
Hong Jiang

Hong Jiang

Xi’an Technological University, School of Computer Science & EngineeringXi’an, China
Buscar este autor en
Sciendo|Google Scholar
Jiang, Hong
  
16 mar 2024
Object Localization Algorithm Based on Meta-Reinforcement Learning's Cover Image
Acerca de este artículo
Artículo anterior
Artículo siguiente
Cite
Descargar portada
Publicado en línea: 16 mar 2024
Páginas: 55 - 65
DOI: https://doi.org/10.2478/ijanmc-2023-0077
Palabras clave
© 2023 Han Yan et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Process of target localization in meta-reinforcement learning
Process of target localization in meta-reinforcement learning

Figure 2.

Object localization model
Object localization model

Figure 3.

Action diagram
Action diagram

Figure 4.

Structure of the location network
Structure of the location network

Figure 5.

Structure of the regression network
Structure of the regression network

Figure 6.

Feature network structure
Feature network structure

Figure 7.

Training process of meta-parameter pooling
Training process of meta-parameter pooling

Figure 8.

Parameter training process of meta-reinforcement learning
Parameter training process of meta-reinforcement learning

Figure 9.

Comparison of training loss functions
Comparison of training loss functions

Figure 10.

Results of ta
Results of ta

Figure 11.

Comparison of precision and recall
Comparison of precision and recall
Idioma:
Inglés
Calendario de la edición:
4 veces al año
Temas de la revista:
Informática, Informática, otros
RSS Feed de revista