Deep Convolutional Ranking for Multilabel Image Annotation
Yunchao Gong, Yangqing Jia, Leung, Thomas et al. · arXiv (Cornell University) · 2013
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.
Cited by 232 works. doi:10.48550/arxiv.1312.4894 Open-access PDF
Authors
References
- ImageNet classification with deep convolutional neural networks
- ImageNet: A large-scale hierarchical image database
- Distinctive Image Features from Scale-Invariant Keypoints
- Improving neural networks by preventing co-adaptation of feature detectors
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
- Large Scale Distributed Deep Networks
- Handwritten Digit Recognition with a Back-Propagation Network
- What is the best multi-stage architecture for object recognition?
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope