资源分类
》 资源 》论文》Nonparametric scene parsing with adaptive feature relevance and semantic context

Nonparametric scene parsing with adaptive feature relevance and semantic context

2019-12-11 | |  60 |   53 |   0

Abstract

This paper presents a nonparametric approach to semantic parsing using small patches and simple gradient, color and location features. We learn the relevance of individual feature channels at test time using a locally adaptive distance metric. To further improve the accuracy of the nonparametric approach, we examine the importance of the retrieval set used to compute the nearest neighbours using a novel semantic descriptor to retrieve better candidates. The approach is validated by experiments on several datasets used for semantic parsing demonstrating the superiority of the method compared to the state of art approaches

上一篇：Detection Evolution with Multi-Order Contextual Co-occurrence

下一篇：Tensor-based High-order Semantic Relation Transfer for Semantic Scene Segmentation

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

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