.png){kind=icon}
返回
Multitask Learning for Object Localization With Deep Reinforcement Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TCDS.2018.2885813.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In object localization, methods based on a top-down search strategy that focus on learning a policy have been widely researched. The performance of these methods relies heavily on the policy in question. This paper proposes a deep Q-network (DQN) that employs a multitask learning method to localize class-specific objects. This DQN agent consists of two parts, an action executor part and a terminal part. The action executor determines the action that the agent should perform and the terminal decides whether the agent has detected the target object. By taking advantage of the capability of feature learning in a multitask method, our method combines these two parts by sharing hidden layers and trains the agent using multitask learning. A detection dataset from the PASCAL visual object classes challenge 2007 was used to evaluate the proposed method, and the results show that it can achieve higher average precision with fewer search steps than similar methods.
Keyword:
Deep Q-network (DQN)
multitask learning
object localization
reinforcement learning (RL)
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4.9
论文数:
1.0K
被引数:
3.5K
机构
引用论文
Advances in the development of built-in diagnostic system for filament wound composite structures
PREAI
分享收藏分享收藏Crystalline‐State Reaction with Allosteric Effect in Spin‐Crossover, Interpenetrated Networks with Magnetic and Optical Bistability具有磁和光学双稳态的自旋交叉，互穿网络中具有变构效应的晶态反应
PREAI
分享收藏CD4 cell count and CD4/CD8 ratio increase during rituximab maintenance in Granulomatosis with polyangiitis patients.png)
PeerJ
OAAI
PeerJIF0
OAAI分享收藏
查看更多内容