Predictor Combination at Test Time

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

Abstract

We present an algorithm for test-time combination of a set of reference predictors with unknown parametric forms. Existing multi-task and transfer learning algorithms focus on training-time transfer and combination, where the parametric forms of predictors are known and shared. However, when the parametric form of a predictor is unknown, e.g., for a human predictor or a predictor in a precompiled library, existing algorithms are not applicable. Instead, we empirically evaluate predictors on sampled data points to measure distances between different predictors. This embeds the set of reference predictors into a Riemannian manifold, upon which we perform manifold denoising to obtain the refined predictor. This allows our approach to make no assumptions about the underlying predictor forms. Our test-time combination algorithm equals or outperforms existing multi-task and transfer learning algorithms on challenging real-world datasets, without introducing specific model assumptions.
LanguageEnglish
Title of host publicationProceedings of the International Conference on Computer Vision (ICCV), 2017
PublisherIEEE
Pages3553-3561
Number of pages9
StatusPublished - 22 Oct 2017

Fingerprint

Learning algorithms

Cite this

Kim, K. I., Tompkin, J., & Richardt, C. (2017). Predictor Combination at Test Time. In Proceedings of the International Conference on Computer Vision (ICCV), 2017 (pp. 3553-3561). IEEE.

Predictor Combination at Test Time. / Kim, Kwang In; Tompkin, James; Richardt, Christian.

Proceedings of the International Conference on Computer Vision (ICCV), 2017. IEEE, 2017. p. 3553-3561.

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

Kim, KI, Tompkin, J & Richardt, C 2017, Predictor Combination at Test Time. in Proceedings of the International Conference on Computer Vision (ICCV), 2017. IEEE, pp. 3553-3561.
Kim KI, Tompkin J, Richardt C. Predictor Combination at Test Time. In Proceedings of the International Conference on Computer Vision (ICCV), 2017. IEEE. 2017. p. 3553-3561
Kim, Kwang In ; Tompkin, James ; Richardt, Christian. / Predictor Combination at Test Time. Proceedings of the International Conference on Computer Vision (ICCV), 2017. IEEE, 2017. pp. 3553-3561
@inproceedings{274ea7720b8b4b818333dfb9bbfb8eb5,
title = "Predictor Combination at Test Time",
abstract = "We present an algorithm for test-time combination of a set of reference predictors with unknown parametric forms. Existing multi-task and transfer learning algorithms focus on training-time transfer and combination, where the parametric forms of predictors are known and shared. However, when the parametric form of a predictor is unknown, e.g., for a human predictor or a predictor in a precompiled library, existing algorithms are not applicable. Instead, we empirically evaluate predictors on sampled data points to measure distances between different predictors. This embeds the set of reference predictors into a Riemannian manifold, upon which we perform manifold denoising to obtain the refined predictor. This allows our approach to make no assumptions about the underlying predictor forms. Our test-time combination algorithm equals or outperforms existing multi-task and transfer learning algorithms on challenging real-world datasets, without introducing specific model assumptions.",
author = "Kim, {Kwang In} and James Tompkin and Christian Richardt",
year = "2017",
month = "10",
day = "22",
language = "English",
pages = "3553--3561",
booktitle = "Proceedings of the International Conference on Computer Vision (ICCV), 2017",
publisher = "IEEE",
address = "USA United States",

}

TY - GEN

T1 - Predictor Combination at Test Time

AU - Kim, Kwang In

AU - Tompkin, James

AU - Richardt, Christian

PY - 2017/10/22

Y1 - 2017/10/22

N2 - We present an algorithm for test-time combination of a set of reference predictors with unknown parametric forms. Existing multi-task and transfer learning algorithms focus on training-time transfer and combination, where the parametric forms of predictors are known and shared. However, when the parametric form of a predictor is unknown, e.g., for a human predictor or a predictor in a precompiled library, existing algorithms are not applicable. Instead, we empirically evaluate predictors on sampled data points to measure distances between different predictors. This embeds the set of reference predictors into a Riemannian manifold, upon which we perform manifold denoising to obtain the refined predictor. This allows our approach to make no assumptions about the underlying predictor forms. Our test-time combination algorithm equals or outperforms existing multi-task and transfer learning algorithms on challenging real-world datasets, without introducing specific model assumptions.

AB - We present an algorithm for test-time combination of a set of reference predictors with unknown parametric forms. Existing multi-task and transfer learning algorithms focus on training-time transfer and combination, where the parametric forms of predictors are known and shared. However, when the parametric form of a predictor is unknown, e.g., for a human predictor or a predictor in a precompiled library, existing algorithms are not applicable. Instead, we empirically evaluate predictors on sampled data points to measure distances between different predictors. This embeds the set of reference predictors into a Riemannian manifold, upon which we perform manifold denoising to obtain the refined predictor. This allows our approach to make no assumptions about the underlying predictor forms. Our test-time combination algorithm equals or outperforms existing multi-task and transfer learning algorithms on challenging real-world datasets, without introducing specific model assumptions.

UR - http://openaccess.thecvf.com/content_iccv_2017/html/Kim_Predictor_Combination_at_ICCV_2017_paper.html

M3 - Conference contribution

SP - 3553

EP - 3561

BT - Proceedings of the International Conference on Computer Vision (ICCV), 2017

PB - IEEE

ER -