Work

Deep Convolutional Ranking for Multilabel Image Annotation

Year: 2013
Type: preprint
Abstract: 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.
Language: English
Open Access status: green
OpenAlex ID: W1514027499
Cites: 35
Cited by: 350
Related to: 10