1. ReinforceNet: A reinforcement learning embedded object detection framework with region selection network
- Author
-
Man Zhou, Rujing Wang, Fangyuan Wang, Liu Liu, Rui Li, Chengjun Xie, and Dengshan Li
- Subjects
0209 industrial biotechnology ,Computer science ,Cognitive Neuroscience ,Feature vector ,media_common.quotation_subject ,02 engineering and technology ,Machine learning ,computer.software_genre ,Convolutional neural network ,020901 industrial engineering & automation ,Artificial Intelligence ,Minimum bounding box ,0202 electrical engineering, electronic engineering, information engineering ,Reinforcement learning ,Function (engineering) ,media_common ,computer.programming_language ,Sequence ,business.industry ,Pascal (programming language) ,Object detection ,Computer Science Applications ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,computer - Abstract
In recent years, researchers have explored reinforcement learning based object detection methods. However, existing methods always suffer from barely satisfactory performance. The main reasons are that current reinforcement learning based methods generate a sequence of inaccurate regions without a reasonable reward function, and regard the non-optimal one at the final step as the detection result for lack of an effective region selection and refinement strategy. To tackle the above problems, we propose a novel reinforcement learning based object detection framework, namely ReinforceNet, possessing the capability of the region selection and refinement by integrating reinforcement learning agents’ action space with Convolutional Neural Network based feature space. In ReinforceNet, we redevelop a reward function that enables the agent to be trained effectively and provide more accurate region proposals. In order to further optimize them, we design Convolutional Neural Network based region selection network (RS-net) and bounding box refinement network (BBR-net). Particularly, the former consists of two sub-networks: Intersection-of-Union network (IoU-net) and Completeness network (CPL-net) which are employed jointly for selecting the optimal region proposal. The latter aims to refine the selected one as the final result. Extensive experimental results on two standard datasets PASCAL VOC 2007 and VOC 2012 demonstrate that ReinforceNet is capable of improving the region selection and learning better agent action representations for reinforcement learning, resulting in the state-of-the-art performance.
- Published
- 2021