Unsupervised learning for maximum consensus robust fitting: A reinforcement learning approach
Author Identifier
Erchuan Zhang
https://orcid.org/0000-0002-4005-5431
David Suter
https://orcid.org/0000-0001-6306-3023
Syed Gilani
Document Type
Journal Article
Publication Title
IEEE Transactions on Pattern Analysis and Machine Intelligence
Publisher
IEEE
School
School of Science
RAS ID
44438
Funders
Australian Research Council
Grant Number
ARC Number : DP200103448
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.
DOI
10.1109/TPAMI.2022.3178442
Access Rights
subscription content
Comments
G. Truong, H. Le, E. Zhang, D. Suter and S. Z. Gilani, (2023). Unsupervised learning for maximum consensus robust fitting: A reinforcement learning approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3), 3890-3903.
https://doi.org/10.1109/TPAMI.2022.3178442