资源分类
》 资源 》论文》Structured Regression Gradient Boosting

Structured Regression Gradient Boosting

2019-12-20 | |  84 |   47 |   0

Abstract

We propose a new way to train a structured output prediction model. More specifically, we train nonlinear data terms in a Gaussian Conditional Random Field (GCRF) bya generalized version of gradient boosting. The approach is evaluated on three challenging regression benchmarks: vessel detection, single image depth estimation and imageinpainting. These experiments suggest that the proposed boosting framework matches or exceeds the state-of-the-art.

上一篇：Learning Aligned Cross-Modal Representations from Weakly Aligned Data

下一篇：Learning Deep Features for Discriminative Localization

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...