Structure-Aware Data Consolidation

Shihao Wu; Peter Bertholet; Hui Huang; Daniel Cohen-Or; Minglun Gong; Matthias Zwicker

doi:https://doi.org/10.1109/TPAMI.2017.2754254

Structure-Aware Data Consolidation

Shihao Wu, Peter Bertholet, Hui Huang, Daniel Cohen-Or, Minglun Gong, Matthias Zwicker

School of Computer Science

Tel Aviv University

Research output: Contribution to journal › Article › peer-review

Abstract

We present a structure-aware technique to consolidate noisy data, which we use as a pre-process for standard clustering and dimensionality reduction. Our technique is related to mean shift, but instead of seeking density modes, it reveals and consolidates continuous high density structures such as curves and surface sheets in the underlying data while ignoring noise and outliers. We provide a theoretical analysis under a Gaussian noise model, and show that our approach significantly improves the performance of many non-linear dimensionality reduction and clustering algorithms in challenging scenarios.

Original language	English
Article number	8046026
Pages (from-to)	2529-2537
Number of pages	9
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	40
Issue number	10
DOIs	https://doi.org/10.1109/TPAMI.2017.2754254
State	Published - 1 Oct 2018

Keywords

Data consolidation
clustering
dimensionality reduction
filtering
manifold denoising

All Science Journal Classification (ASJC) codes

Software
Computer Vision and Pattern Recognition
Computational Theory and Mathematics
Artificial Intelligence
Applied Mathematics

Access to Document

https://doi.org/10.1109/TPAMI.2017.2754254

Cite this

@article{557e4ed97405463eab31339fef5f0d5d,

title = "Structure-Aware Data Consolidation",

abstract = "We present a structure-aware technique to consolidate noisy data, which we use as a pre-process for standard clustering and dimensionality reduction. Our technique is related to mean shift, but instead of seeking density modes, it reveals and consolidates continuous high density structures such as curves and surface sheets in the underlying data while ignoring noise and outliers. We provide a theoretical analysis under a Gaussian noise model, and show that our approach significantly improves the performance of many non-linear dimensionality reduction and clustering algorithms in challenging scenarios.",

keywords = "Data consolidation, clustering, dimensionality reduction, filtering, manifold denoising",

author = "Shihao Wu and Peter Bertholet and Hui Huang and Daniel Cohen-Or and Minglun Gong and Matthias Zwicker",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.",

year = "2018",

month = oct,

day = "1",

doi = "https://doi.org/10.1109/TPAMI.2017.2754254",

language = "الإنجليزيّة",

volume = "40",

pages = "2529--2537",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE Computer Society",

number = "10",

}

TY - JOUR

T1 - Structure-Aware Data Consolidation

AU - Wu, Shihao

AU - Bertholet, Peter

AU - Huang, Hui

AU - Cohen-Or, Daniel

AU - Gong, Minglun

AU - Zwicker, Matthias

PY - 2018/10/1

Y1 - 2018/10/1

N2 - We present a structure-aware technique to consolidate noisy data, which we use as a pre-process for standard clustering and dimensionality reduction. Our technique is related to mean shift, but instead of seeking density modes, it reveals and consolidates continuous high density structures such as curves and surface sheets in the underlying data while ignoring noise and outliers. We provide a theoretical analysis under a Gaussian noise model, and show that our approach significantly improves the performance of many non-linear dimensionality reduction and clustering algorithms in challenging scenarios.

AB - We present a structure-aware technique to consolidate noisy data, which we use as a pre-process for standard clustering and dimensionality reduction. Our technique is related to mean shift, but instead of seeking density modes, it reveals and consolidates continuous high density structures such as curves and surface sheets in the underlying data while ignoring noise and outliers. We provide a theoretical analysis under a Gaussian noise model, and show that our approach significantly improves the performance of many non-linear dimensionality reduction and clustering algorithms in challenging scenarios.

KW - Data consolidation

KW - clustering

KW - dimensionality reduction

KW - filtering

KW - manifold denoising

UR - http://www.scopus.com/inward/record.url?scp=85030654112&partnerID=8YFLogxK

U2 - https://doi.org/10.1109/TPAMI.2017.2754254

DO - https://doi.org/10.1109/TPAMI.2017.2754254

M3 - مقالة

SN - 0162-8828

VL - 40

SP - 2529

EP - 2537

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 10

M1 - 8046026

ER -

Structure-Aware Data Consolidation

Abstract

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this