Deep Convolutional Ranking for Multilabel Image Annotation
This addresses multilabel image tagging for computer vision applications, representing an incremental improvement.
The paper tackled multilabel image annotation by combining convolutional architectures with approximate top-k ranking objectives, achieving about 10% performance gain over conventional visual features on the NUS-WIDE dataset.
Multilabel image annotation is one of the most important challenges in computer vision with many real-world applications. While existing work usually use conventional 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 components that lead to better performances. Specifically, we show that a significant performance 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 conventional visual features by about 10%, obtaining the best reported performance in the literature.