资源分类
》 资源 》论文》Probabilistic Label Trees for Efficient Large Scale Image Classification

Probabilistic Label Trees for Efficient Large Scale Image Classification

2019-11-28 | |  63 |   40 |   0

Abstract Large-scale recognition problems with thousands of classes pose a particular challenge because applying the classififier requires more computation as the number of classes grows. The label tree model integrates classifification with the traversal of the tree so that complexity grows logarithmically. In this paper, we show how the parameters of the label tree can be found using maximum likelihood estimation. This new probabilistic learning technique produces a label tree with signifificantly improved recognition accuracy.

上一篇：Studying Relationships BetweenHuman Gaze, Description, and Computer Vision

下一篇：Supervised Semantic Gradient Extraction Using Linear-Time Optimization

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...

  • A Mathematical Mo...

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

  • Rating-Boosted La...

    The performance of a recommendation system reli...