Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking

James Tompkin, Kwang In Kim, Hanspeter Pfister, Christian Theobalt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Large databases are often organized by hand-labeled metadata—or criteria—which are expensive to collect. We can use unsupervised learning to model database variation, but these models are often high dimensional, complex to parameterize, or require expert knowledge. We learn low-dimensional continuous criteria via interactive ranking, so that the novice user need only describe the relative ordering of examples. This is formed as semi-supervised label propagation in which we maximize the information gained from a limited number of examples. Further, we actively suggest data points to the user to rank in a more informative way than existing work. Our efficient approach allows users to interactively organize thousands of data points along 1D and 2D continuous sliders. We experiment with databases of imagery and geometry to demonstrate that our tool is useful for quickly assessing and organizing the content of large databases.
LanguageEnglish
Title of host publicationProc. British Machine Vision Conference, 2017
StatusPublished - 2017
EventBMVC 2017: The British Machine Vision Conference -
Duration: 4 Sep 20177 Sep 2017

Conference

ConferenceBMVC 2017: The British Machine Vision Conference
Period4/09/177/09/17

Fingerprint

Unsupervised learning
Metadata
Labels
Geometry
Experiments

Cite this

Tompkin, J., Kim, K. I., Pfister, H., & Theobalt, C. (2017). Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking. In Proc. British Machine Vision Conference, 2017

Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking. / Tompkin, James; Kim, Kwang In; Pfister, Hanspeter; Theobalt, Christian.

Proc. British Machine Vision Conference, 2017. 2017.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tompkin, J, Kim, KI, Pfister, H & Theobalt, C 2017, Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking. in Proc. British Machine Vision Conference, 2017. BMVC 2017: The British Machine Vision Conference, 4/09/17.
Tompkin J, Kim KI, Pfister H, Theobalt C. Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking. In Proc. British Machine Vision Conference, 2017. 2017
Tompkin, James ; Kim, Kwang In ; Pfister, Hanspeter ; Theobalt, Christian. / Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking. Proc. British Machine Vision Conference, 2017. 2017.
@inproceedings{4f7cd8b2dcbf4adfa54dc3b5e78fa2e4,
title = "Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking",
abstract = "Large databases are often organized by hand-labeled metadata—or criteria—which are expensive to collect. We can use unsupervised learning to model database variation, but these models are often high dimensional, complex to parameterize, or require expert knowledge. We learn low-dimensional continuous criteria via interactive ranking, so that the novice user need only describe the relative ordering of examples. This is formed as semi-supervised label propagation in which we maximize the information gained from a limited number of examples. Further, we actively suggest data points to the user to rank in a more informative way than existing work. Our efficient approach allows users to interactively organize thousands of data points along 1D and 2D continuous sliders. We experiment with databases of imagery and geometry to demonstrate that our tool is useful for quickly assessing and organizing the content of large databases.",
author = "James Tompkin and Kim, {Kwang In} and Hanspeter Pfister and Christian Theobalt",
year = "2017",
language = "English",
booktitle = "Proc. British Machine Vision Conference, 2017",

}

TY - GEN

T1 - Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking

AU - Tompkin, James

AU - Kim, Kwang In

AU - Pfister, Hanspeter

AU - Theobalt, Christian

PY - 2017

Y1 - 2017

N2 - Large databases are often organized by hand-labeled metadata—or criteria—which are expensive to collect. We can use unsupervised learning to model database variation, but these models are often high dimensional, complex to parameterize, or require expert knowledge. We learn low-dimensional continuous criteria via interactive ranking, so that the novice user need only describe the relative ordering of examples. This is formed as semi-supervised label propagation in which we maximize the information gained from a limited number of examples. Further, we actively suggest data points to the user to rank in a more informative way than existing work. Our efficient approach allows users to interactively organize thousands of data points along 1D and 2D continuous sliders. We experiment with databases of imagery and geometry to demonstrate that our tool is useful for quickly assessing and organizing the content of large databases.

AB - Large databases are often organized by hand-labeled metadata—or criteria—which are expensive to collect. We can use unsupervised learning to model database variation, but these models are often high dimensional, complex to parameterize, or require expert knowledge. We learn low-dimensional continuous criteria via interactive ranking, so that the novice user need only describe the relative ordering of examples. This is formed as semi-supervised label propagation in which we maximize the information gained from a limited number of examples. Further, we actively suggest data points to the user to rank in a more informative way than existing work. Our efficient approach allows users to interactively organize thousands of data points along 1D and 2D continuous sliders. We experiment with databases of imagery and geometry to demonstrate that our tool is useful for quickly assessing and organizing the content of large databases.

M3 - Conference contribution

BT - Proc. British Machine Vision Conference, 2017

ER -