Robust data whitening as an iteratively re-weighted least squares problem

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00312642" target="_blank" >RIV/68407700:21230/17:00312642 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.1007/978-3-319-59126-1_20" target="_blank" >http://dx.doi.org/10.1007/978-3-319-59126-1_20</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-59126-1_20" target="_blank" >10.1007/978-3-319-59126-1_20</a>

Result language

angličtina

Original language name

Robust data whitening as an iteratively re-weighted least squares problem

Original language description

The entries of high-dimensional measurements, such as image or feature descriptors, are often correlated, which leads to a bias in similarity estimation. To remove the correlation, a linear transformation, called whitening, is commonly used. In this work, we analyze robust estimation of the whitening transformation in the presence of outliers. Inspired by the Iteratively Re-weighted Least Squares approach, we iterate between centering and applying a transformation matrix, a process which is shown to converge to a solution that minimizes the sum of ℓ2 norms. The approach is developed for unsupervised scenarios, but further extend to supervised cases. We demonstrate the robustness of our method to outliers on synthetic 2D data and also show improvements compared to conventional whitening on real data for image retrieval with CNN-based representation. Finally, our robust estimation is not limited to data whitening, but can be used for robust patch rectification, e.g. with MSER features.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/LL1303" target="_blank" >LL1303: Large Scale Category Retrieval</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year

2017

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Image Analysis

ISBN

978-3-319-59125-4

ISSN

0302-9743

e-ISSN

—

Number of pages

14

Pages from-to

234-247

Publisher name

Springer International Publishing

Place of publication

Cham

Event location

Tromso

Event date

Jun 12, 2017

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—