Unsupervised Learning for Robust Fitting: A Reinforcement Learning Approach

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

doi:10.1109/cvpr46437.2021.01021

Cited by 9 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning is also used to solve various problems. Algorithms from machine learning are divided into three categories, which is supervised learning, unsupervised learning, and reinforcement learning [8].…”

Section: Studi Literature a Machine Learningmentioning

confidence: 99%

Machine Learning Approach to Determine the Drug-Prone Areas in Lhokseumawe City, Indonesia

2022

IJMRA

View full text Add to dashboard Cite

This research aims to apply Machine Learning algorithms, such as K-means and K-nearest neighbor into a system that can determine drug-prone areas in Lhokseumawe City, Indonesia. The results of the k-means calculation in some clusters of areas that are very prone, prone and not prone to drugs based on drug user data with some criterias, namely the number of users, sub- district, education, occupation and types of drugs. Based on the research that tested by using the k-means algorithm on data on drug users in 2018-2021, the average percentage of clusters in very prone areas is 49.50%, the percentage of clusters in prone areas is 29.26% and the percentage of clusters in non-prone areas is 21.23%. Furthermore, the results of testing with the K-NN algorithm with 98 training data and 20 testing data obtained an average accuracy value of 87%.

show abstract

Section: Studi Literature a Machine Learningmentioning

confidence: 99%

Machine Learning Approach to Determine the Drug-Prone Areas in Lhokseumawe City, Indonesia

2022

IJMRA

View full text Add to dashboard Cite

show abstract

“…Partly buoyed by the dominance of deep learning in computer vision, learning-based solutions to robust geometric fitting have been developed [10,62,72]. Such techniques leverage statistics in large datasets to learn a mapping from the input instance to the desired solution.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Quantum-Classical Algorithm for Robust Fitting

Doan¹,

Sasdelli²,

Suter³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Fitting geometric models onto outlier contaminated data is provably intractable. Many computer vision systems rely on random sampling heuristics to solve robust fitting, which do not provide optimality guarantees and error bounds. It is therefore critical to develop novel approaches that can bridge the gap between exact solutions that are costly, and fast heuristics that offer no quality assurances. In this paper, we propose a hybrid quantum-classical algorithm for robust fitting. Our core contribution is a novel robust fitting formulation that solves a sequence of integer programs and terminates with a global solution or an error bound. The combinatorial subproblems are amenable to a quantum annealer, which helps to tighten the bound efficiently. While our usage of quantum computing does not surmount the fundamental intractability of robust fitting, by providing error bounds our algorithm is a practical improvement over randomised heuristics. Moreover, our work represents a concrete application of quantum computing in computer vision. We present results obtained using an actual quantum computer (D-Wave Advantage) and via simulation 1 .

show abstract

“…However, this method is slow in general, despite speedups introduced by Cai et al [2]. In [25], an unsupervised learning approach was proposed to determine which point in a basis to remove in solving robust model fitting problems. This approach adopted the framework of reinforcement learning, where removing points are guided by maximising rewards.…”

Section: Introductionmentioning

confidence: 99%

“…Like many learning based approaches, it may take a long time to train and it is hard to analyse the method and its ability to generalise. Like [25] and [24], modifications to the basic tree search that lose the priority queue guarantees of A * , sacrifice optimality guarantees for speed. This paper is also spiritually in that context.…”

Section: Introductionmentioning

confidence: 99%

Maximum Consensus by Weighted Influences of Monotone Boolean Functions

Zhang¹,

Suter²,

Tennakoon³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Robust model fitting is a fundamental problem in computer vision: used to pre-process raw data in the presence of outliers. Maximisation of Consensus (MaxCon) is one of the most popular robust criteria and widely used. Recently (Tennakoon et al. CVPR2021), a connection has been made between MaxCon and estimation of influences of a Monotone Boolean function. Equipping the Boolean cube with different measures and adopting different sampling strategies (two sides of the same coin) can have differing effects: which leads to the current study. This paper studies the concept of weighted influences for solving MaxCon. In particular, we study endowing the Boolean cube with the Bernoulli measure and performing biased (as opposed to uniform) sampling. Theoretically, we prove the weighted influences, under this measure, of points belonging to larger structures are smaller than those of points belonging to smaller structures in general. We also consider another "natural" family of sampling/weighting strategies, sampling with uniform measure concentrated on a particular (Hamming) level of the cube.Based on weighted sampling, we modify the algorithm of Tennakoon et al., and test on both synthetic and real datasets. This paper is not promoting a new approach per se, but rather studying the issue of weighted sampling. Accordingly, we are not claiming to have produced a superior algorithm: rather we show some modest gains of Bernoulli sampling, and we illuminate some of the interactions between structure in data and weighted sampling.

show abstract

Unsupervised Learning for Robust Fitting: A Reinforcement Learning Approach

Cited by 9 publications

References 22 publications

Machine Learning Approach to Determine the Drug-Prone Areas in Lhokseumawe City, Indonesia

Machine Learning Approach to Determine the Drug-Prone Areas in Lhokseumawe City, Indonesia

A Hybrid Quantum-Classical Algorithm for Robust Fitting

Maximum Consensus by Weighted Influences of Monotone Boolean Functions

Contact Info

Product

Resources

About