Enhancing Multi-Step Action Prediction for Active Object Detection

Page view(s)
28
Checked on Oct 25, 2024
Enhancing Multi-Step Action Prediction for Active Object Detection
Title:
Enhancing Multi-Step Action Prediction for Active Object Detection
Journal Title:
2021 IEEE International Conference on Image Processing (ICIP)
Keywords:
Publication Date:
23 August 2021
Citation:
Fang, F., Xu, Q., Gauthier, N., Li, L., & Lim, J.-H. (2021). Enhancing Multi-Step Action Prediction for Active Object Detection. 2021 IEEE International Conference on Image Processing (ICIP). doi:10.1109/icip42928.2021.9506078
Abstract:
Active vision for robots is one promising solution to open world visual detection problems. A fundamental issue is view planning, i.e., predicting next best views to capture images of interest to reduce uncertainty. While multi-step action in a reinforcement learning (RL) setup can boost the efficiency of view planning, existing methods suffer from unstable detection outcome when the Q-values of multiple branches of action advantages (i.e., action range and action type) are combined naively. To tackle this issue, we propose a novel mechanism to disentangle action range from action type through a two-stage training strategy on a deep Q-network. It combines well-crafted loss functions with respect to action range and action type to enforce separated training of these two branches. We evaluate our method on two public datasets and show that it facilitates substantial gain in view planning efficiency, while enhancing detection accuracy.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research - AME Programmatic Funding Scheme
Grant Reference no. : A18A2b0046
Description:
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
2381-8549
1522-4880
ISBN:
978-1-6654-4115-5
978-1-6654-3102-6
Files uploaded:

File Size Format Action
icip-2021-1472-camera-ready.pdf 393.39 KB PDF Open