Published on Fri Mar 05 2021

Unsupervised Learning for Robust Fitting:A Reinforcement Learning Approach

Giang Truong, Huu Le, David Suter, Erchuan Zhang, Syed Zulqarnain Gilani
0
0
0
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.

Wed Oct 21 2020
Computer Vision
Progressive Batching for Efficient Non-linear Least Squares
Non-linear least squares solvers are used across a broad range of offline and real-time model fitting problems. Most improvements of the basic Gauss-Newton algorithm tackle convergence guarantees or leverage the sparsity of the problem structure.
0
0
0
Thu Jul 13 2017
Computer Vision
Discriminative Optimization: Theory and Applications to Computer Vision Problems
Discriminative Optimization (DO) learns search directions from data without the need of a cost function. DO explicitly learns a sequence of updates in the search space that leads to stationary points that correspond to desired solutions.
0
0
0
Sun Feb 18 2018
Computer Vision
Robust Fitting in Computer Vision: Easy or Hard?
Robust model fitting plays a vital role in computer vision. Research into algorithms for robust fitting continues to be active. consensus maximisation is the most popular way to find the model parameters that maximise the number of inliers.
0
0
0
Thu Mar 22 2018
Computer Vision
Maximum Consensus Parameter Estimation by Reweighted Methods
Robust parameter estimation in computer vision is frequently accomplished by solving the maximum consensus (MaxCon) problem. Widely used randomized methods can only produce {random} approximate solutions, while global methods are too slow to exercise on realistic problem sizes.
0
0
0
Mon Dec 07 2015
Machine Learning
Pseudo-Bayesian Robust PCA: Algorithms and Analyses
robust PCA is an attempt to reduce the sensitivity of classical PCA to unwanted outliers. The resulting optimization problem is typically NP-hard. We propose a novel pseudo-Bayesian algorithm that explicitly compensates for design weaknesses in many existing approaches.
0
0
0
Mon Apr 13 2015
Machine Learning
Learning Multiple Visual Tasks while Discovering their Structure
Multi-task learning is a natural approach for computer vision applications that require the simultaneous solution of several distinct but related problems. The key idea is that exploring task relatedness can lead to improved performances.
0
0
0