Unsupervised Learning for Robust Fitting: A Reinforcement Learning Approach

Giang Truong, Huu Le, David Suter, Erchuan Zhang, Syed Zulqarnain Gilani

Abstract: Robust model fitting is a core algorithm in a large num- ber of computer vision applications. Solving this prob- lem efficiently for datasets highly contaminated with out- liers is, however, still challenging due to the underlying computational complexity. Recent literature has focused on learning-based algorithms. However, most approaches are supervised (which require a large amount of labelled training data). In this paper, we introduce a novel unsuper- vised learning framework that learns to directly solve robust model fitting. Unlike other methods, our work is agnostic to the underlying input features, and can be easily gener- alized to a wide variety of LP-type problems with quasi- convex residuals. We empirically show that our method out- performs existing unsupervised learning approaches, and achieves competitive results compared to traditional meth- ods on several important computer vision problems