Loading...
Loading...

Go to the content (press return)

Hierarchical object detection with deep reinforcement learning

Author
Bellver, M.; Giro, X.; Marques, F.; Torres, J.
Type of activity
Presentation of work at congresses
Name of edition
Third Deep Reinforcement Learning Workshop
Date of publication
2016
Presentation's date
2016-12-16
Book of congress proceedings
Deep Reinforcement Learning Workshop: NIPS 2016
First page
1
Last page
9
Repository
http://hdl.handle.net/2117/98760 Open in new window
https://imatge-upc.github.io/detection-2016-nipsws/ Open in new window
URL
https://sites.google.com/site/deeprlnips2016/ Open in new window
Abstract
We present a method for performing hierarchical object detection in images guided by a deep reinforcement learning agent. The key idea is to focus on those parts of the image that contain richer information and zoom on them. We train an intelligent agent that, given an image window, is capable of deciding where to focus the attention among five different predefined region candidates (smaller windows). This procedure is iterated providing a hierarchical image analysis. We compare two different ...
Citation
Bellver, M., Giro, X., Marques, F., Torres, J. Hierarchical object detection with deep reinforcement learning. A: Deep Reinforcement Learning Workshop. "Deep Reinforcement Learning Workshop, NIPS 2016". Barcelona: 2016.
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants

Attachments