Deep Convolutional Ranking for Multilabel Image Annotation 论文

摘要

Multilabel image annotation is one of the most important challenges in computer vision with many real-world applications. While existing work usually use con-ventional visual features for multilabel annotation, features based on Deep Neural Networks have shown potential to significantly boost performance. In this work, we propose to leverage the advantage of such features and analyze key compo-nents that lead to better performances. Specifically, we show that a significant per-formance gain could be obtained by combining convolutional architectures with approximate top-k ranking objectives, as thye naturally fit the multilabel tagging problem. Our experiments on the NUS-WIDE dataset outperforms the conven-tional visual features by about 10%, obtaining the best reported performance in the literature. 1