Unsupervised Learning for Robust Fitting:A Reinforcement Learning Approach

TL;DR

This paper introduces an unsupervised reinforcement learning framework for robust model fitting in computer vision, capable of handling outliers efficiently without requiring labeled data, and generalizable across various LP-type problems.

Contribution

The work presents a novel unsupervised learning approach for robust model fitting that is agnostic to input features and applicable to multiple problem types, outperforming existing unsupervised methods.

Findings

Outperforms existing unsupervised learning approaches

Achieves competitive results with traditional methods

Generalizes to various LP-type problems

Abstract

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.