Unsupervised Learning for Robust Fitting:A Reinforcement Learning Approach
This addresses the challenge of robust fitting in highly contaminated datasets for computer vision applications, offering an unsupervised alternative to supervised approaches.
The paper tackles robust model fitting in computer vision by introducing an unsupervised learning framework that avoids the need for labeled data, achieving competitive results compared to traditional methods on several vision problems.
Robust model fitting is a core algorithm in a large number of computer vision applications. Solving this problem efficiently for datasets highly contaminated with outliers 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 unsupervised 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 generalized to a wide variety of LP-type problems with quasi-convex residuals. We empirically show that our method outperforms existing unsupervised learning approaches, and achieves competitive results compared to traditional methods on several important computer vision problems.