Unsupervised Learning for Maximum Consensus Robust Fitting: A Reinforcement Learning Approach
Artikel i vetenskaplig tidskrift, 2023

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.

Maximum consensus

reinforcement learning

robust fitting


Giang Truong

Edith Cowan University

Huu Le

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik

Erchuan Zhang

Edith Cowan University

David Suter

Edith Cowan University

Syed Zulqarnain Gilani

Edith Cowan University

IEEE Transactions on Pattern Analysis and Machine Intelligence

0162-8828 (ISSN)

Vol. 45 3 3890-3903


Annan data- och informationsvetenskap

Bioinformatik (beräkningsbiologi)

Datorseende och robotik (autonoma system)



Mer information

Senast uppdaterat