Predictor Combination At Test Time
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)(2017)
摘要
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.
更多查看译文
关键词
predictor combination,test time,reference predictors,unknown parametric forms,transfer learning algorithms,training-time transfer,human predictor,test-time combination algorithm,predictor forms,data points,Riemannian manifold,manifold denoising
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络