Automatic Inside Point Localization with Deep Reinforcement Learning for Interactive Object Segmentation

Automatic Inside Point Localization with Deep Reinforcement Learning for Interactive Object Segmentation

In the task of interactive image segmentation, the Inside-Outside Guidance (IOG) algorithm has demonstrated superior segmentation performance leveraging Inside-Outside Guidance information. Nevertheless, we observe that the inconsistent input between training and testing when selecting the inside po...

Full description

Bibliographic Details
Main Authors: Guoqing Li, Guoping Zhang, Chanchan Qin
Format: Article
Language:English
Published: MDPI AG 2021-09-01
Series:Sensors
Subjects:
interactive image segmentation
Markov Decision Process (MDP)
Deep Reinforcement Learning (DRL)
inside point localization
Deep Q-Network (DQN)
Online Access:https://www.mdpi.com/1424-8220/21/18/6100

Internet

https://www.mdpi.com/1424-8220/21/18/6100

Similar Items