Unsupervised Learning for Maximum Consensus Robust Fitting: A Reinforcement Learning Approach
| dc.contributor.author | Truong, G. | |
| dc.contributor.author | Le, H. | |
| dc.contributor.author | Zhang, E. | |
| dc.contributor.author | Suter, D. | |
| dc.contributor.author | Gilani, S.Z. | |
| dc.date.issued | 2023 | |
| dc.description.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. | |
| dc.description.statementofresponsibility | Giang Truong, Huu Le, Erchuan Zhang, David Suter, and Syed Zulqarnain Gilani | |
| dc.identifier.citation | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023; 45(3):3890-3903 | |
| dc.identifier.doi | 10.1109/TPAMI.2022.3178442 | |
| dc.identifier.issn | 0162-8828 | |
| dc.identifier.issn | 1939-3539 | |
| dc.identifier.orcid | Suter, D. [0000-0001-6306-3023] | |
| dc.identifier.uri | https://hdl.handle.net/2440/139772 | |
| dc.language.iso | en | |
| dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | |
| dc.relation.grant | http://purl.org/au-research/grants/arc/DP200103448 | |
| dc.rights | © 2022 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. | |
| dc.source.uri | https://doi.org/10.1109/tpami.2022.3178442 | |
| dc.subject | Maximum consensus; robust fitting; reinforcement learning | |
| dc.title | Unsupervised Learning for Maximum Consensus Robust Fitting: A Reinforcement Learning Approach | |
| dc.type | Journal article | |
| pubs.publication-status | Published |