Gated Value Network for Multilabel Classification

doi:10.1109/TNNLS.2020.3019804

Gated Value Network for Multilabel Classification

2021-10-01

2

PRE

AI

DOI：10.1109/TNNLS.2020.3019804

原文链接

原文求助

摘要

En 中文

We introduce a gated value network (GVN) for general multilabel classification (MLC) tasks. GVN was motivated by deep value network (DVN) that directly exploits the compatibility metric as the learning pursuit for MLC. Meanwhile, it further improves traditional DVN on twofold. First, GVN relaxes the complex variable optimization steps in DVN inference by incorporating a feedforward predictor for straightforward multilabel prediction. Second, GVN also introduces the gating mechanism to block confounding factors from the input data that allows more precise compatibility evaluations for data and their potential multilabels. The whole GVN framework is trained in an end-to-end manner with policy gradient approaches. We show the effectiveness and generalization of GVN on diverse learning tasks, including document classification, audio tagging, and image attribute prediction.

Keyword:

Logic gates

Optimization

Task analysis

Tagging

Machine learning

Learning systems

Visualization

Feedforward predict

gated value network (GVN)

multilabel classification (MLC)

Gated Value Network for Multilabel Classification

摘要

AI总结

期刊

机构

引用论文