Toward real-time image annotation using marginalized coupled dictionary learning

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 regularization on semantic prototypes to preserve the sparse and imbalanced nature of labels

Recommended citation: Roostaiyan, S. M., Hosseini, M. M., Kashani, M. M., & Amiri, S. H. (2022). " Toward real-time image annotation using marginalized coupled dictionary learning." Journal of Real-Time Image Processing, 19(3), 623-638. https://arxiv.org/abs/2304.06907