Toward Real-Time Image Annotation Using Marginalized Coupled Dictionary Learning

Abstract

In most image retrieval systems, images include various high-level semantics, called tags or annotations. Virtually all the state-of-the-art image annotation methods that handle imbalanced labeling are search-based techniques which are time-consuming. In this paper, a novel coupled dictionary learning approach is proposed to learn a limited number of visual prototypes and their corresponding semantics simultaneously. This approach leads to a real-time image annotation procedure. Another contribution of this paper is that utilizes a marginalized loss function instead of the squared loss function that is inappropriate for image annotation with imbalanced labels. We have employed a marginalized loss function in our method to leverage a simple and effective method of prototype updating. Meanwhile, we have introduced ${\ell }_1$ regularization on semantic prototypes to preserve the sparse and imbalanced nature of labels in learned semantic prototypes. Finally, comprehensive experimental results on various datasets demonstrate the efficiency of the proposed method for image annotation tasks in terms of accuracy and time. The reference implementation is publicly available on https://github.com/hamid-amiri/MCDL-Image-Annotation.

arXiv comment@article{roostaiyan2022toward, title={Toward real-time image annotation using marginalized coupled dictionary learning}, author={Roostaiyan, Seyed Mahdi and Hosseini, Mohammad Mehdi and Kashani, Mahya Mohammadi and Amiri, S Hamid}, journal={Journal of Real-Time Image Processing}, volume={19}, number={3}, pages={623--638}, year={2022}, publisher={Springer} }

References in corpus (13)

• Least Angle Regression
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Rejoinder to "Least angle regression" by Efron et al
• Cross-label Suppression: A Discriminative and Fast Dictionary Learning with Group Regularization
• Rethinking Interactive Image Segmentation: Feature Space Annotation
• Multimodal Image Denoising based on Coupled Dictionary Learning