Active Object Localization with Deep Reinforcement Learning
Authors:
- Juan C. CaicedoJCJuan C. Caicedo
- Svetlana LazebnikSLSvetlana Lazebnik
- 1 December 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2488-2496
Abstract
We present an active detection model for localizing objects in scenes. The model is class-specific and allows an agent to focus attention on candidate regions for identifying the correct location of a target object. This agent learns to deform a bounding box using simple transformation actions, with the goal of determining the most specific location of target objects following top-down reasoning. The proposed localization agent is trained using deep reinforcement learning, and evaluated on the Pascal VOC 2007 dataset. We show that agents guided by the proposed model are able to localize a single instance of an object after analyzing only between 11 and 25 regions in an image, and obtain the best detection results among systems that do not use object proposals for object localization.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- An active search strategy for efficient object class detection2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Edge Boxes: Locating Object Proposals from Edges2014
- Visualizing and Understanding Convolutional Networks2014
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Diagnosing Error in Object Detectors2012
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Contextual guidance of eye movements and attention in real-world scenes: The role of global features in object search.Psychological Review, 2006
- Computational modelling of visual attentionNature Reviews Neuroscience, 2001