ICRA 2011 Paper Abstract


Paper WeA114.1

Zheng, Yuhua (Stevens Institute of Technology), Meng, Yan (Stevens Institute of Technology)

Modular Neural Networks for Multi-Class Object Recognition

Scheduled for presentation during the Regular Sessions "Computer Vision for Robotics and Automation I" (WeA114), Wednesday, May 11, 2011, 08:20−08:35, Room 5J

2011 IEEE International Conference on Robotics and Automation, May 9-13, 2011, Shanghai International Conference Center, Shanghai, China

This information is tentative and subject to change. Compiled on July 14, 2020

Keywords Computer Vision for Robotics and Automation, Recognition


Multi-class object recognition is a critical capability for an intelligence robot to perceive its environment. In this paper, a new approach consisting of a number of modular neural networks is proposed to recognize multiple classes of objects for a robotic system. The population of the modular neural networks depends on the class number of the objects to be recognized and each modular network only focuses on learning one object class. For each modular neural network, both the bottom-up (sensory-driven) and top-down (expectation-driven) pathways are fused together, and a supervised learning algorithm is applied to update corresponding weights of both pathways. Furthermore, two different training strategies are evaluated: positive-only training and positive-and-negative training. Experiments on visual image recognition demonstrate the efficiencies of the proposed approach and the corresponding training strategies.



Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2020 PaperCept, Inc.
Page generated 2020-07-14  15:35:56 PST  Terms of use