Predictor Combination at Test Time

Kwang In Kim, James Tompkin, Christian Richardt

Research output: Chapter or section in a book/report/conference proceedingChapter in a published conference proceeding

4 Citations (SciVal)


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 languageEnglish
Title of host publicationProceedings of the International Conference on Computer Vision (ICCV), 2017
Number of pages9
Publication statusPublished - 22 Oct 2017


Dive into the research topics of 'Predictor Combination at Test Time'. Together they form a unique fingerprint.

Cite this