Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/139772
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Journal article |
Title: | Unsupervised Learning for Maximum Consensus Robust Fitting: A Reinforcement Learning Approach |
Author: | Truong, G. Le, H. Zhang, E. Suter, D. Gilani, S.Z. |
Citation: | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023; 45(3):3890-3903 |
Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
Issue Date: | 2023 |
ISSN: | 0162-8828 1939-3539 |
Statement of Responsibility: | Giang Truong, Huu Le, Erchuan Zhang, David Suter, and Syed Zulqarnain Gilani |
Abstract: | Robust model fitting is a core algorithm in several computer vision applications. Despite being studied for decades, solving this problem efficiently for datasets that are heavily contaminated by outliers is still challenging: due to the underlying computational complexity. A recent focus has been on learning-based algorithms. However, most of these approaches are supervised (which require a large amount of labelled training data). In this paper, we introduce a novel unsupervised learning framework: that learns to directly (without labelled data) solve robust model fitting. Moreover, unlike other learning-based methods, our work is agnostic to the underlying input features, and can be easily generalized to a wide variety of LP-type problems with quasi-convex residuals. We empirically show that our method outperforms existing (un)supervised learning approaches, and also achieves competitive results compared to traditional (non-learning-based) methods. Our approach is designed to try to maximise consensus (MaxCon), similar to the popular RANSAC. The basis of our approach, is to adopt a Reinforcement Learning framework. This requires designing appropriate reward functions, and state encodings. We provide a family of reward functions, tunable by choice of a parameter. We also investigate the application of different basic and enhanced Q-learning components. |
Keywords: | Maximum consensus; robust fitting; reinforcement learning |
Rights: | © 2022 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. |
DOI: | 10.1109/TPAMI.2022.3178442 |
Grant ID: | http://purl.org/au-research/grants/arc/DP200103448 |
Published version: | http://dx.doi.org/10.1109/tpami.2022.3178442 |
Appears in Collections: | Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.