Multimedia Classification Using Bipolar Relation Graphs

doi:10.1109/TMM.2017.2689922

Multimedia Classification Using Bipolar Relation Graphs

2017-08-01

2

PRE

AI

DOI：10.1109/TMM.2017.2689922

原文链接

原文求助

摘要

En 中文

Recent studies on category relations have shown the promising progress in addressing classification problems. Existing works independently consider the known relation and classifier optimization, and thus restrain the room for performance improvement. In this work, a new loss function is proposed to leverage the underlining relations among categories and classifiers. In addition, the bipolar relation (BR) graph is employed to formulate a general form for diverse relations. This bipolar graph is automatically learnt for reliving the constraints which may happen during the cost minimization. Extensive experiments on three benchmarks with various hypotheses and graphs demonstrate that our method can offer a significant performance improvement by jointly learning from both BR graph and hypothesis, in particular on a small training dataset scenario that suffers from severe overfitting problem.

Keyword:

Classification

loss function

multimedia retrieval

optimization

Multimedia Classification Using Bipolar Relation Graphs

摘要

AI总结

期刊

机构