Projects per year
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.
Original language | English |
---|---|
Title of host publication | Proceedings of the International Conference on Computer Vision (ICCV), 2017 |
Publisher | IEEE |
Pages | 3553-3561 |
Number of pages | 9 |
Publication status | Published - 22 Oct 2017 |
Fingerprint Dive into the research topics of 'Predictor Combination at Test Time'. Together they form a unique fingerprint.
Projects
-
Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA)
Cosker, D., Campbell, N., Fincham Haines, T., Hall, P., Kim, K. I., Lutteroth, C., O'Neill, E., Richardt, C. & Yang, Y.
Engineering and Physical Sciences Research Council
1/09/15 → 28/02/21
Project: Research council
-
Personalized Exploration of Imagery Database
Kim, K. I.
Engineering and Physical Sciences Research Council
1/09/16 → 31/05/17
Project: Research council