A novel image tag completion method based on convolutional neural network
This addresses the issue of incomplete tags for image retrieval and annotation users, but it appears incremental as it builds on existing CNN methods.
The paper tackles the problem of incomplete image tags in retrieval and annotation by proposing a novel method that jointly learns CNN parameters, a linear predictor, and complete tags through a minimization problem, showing effectiveness in experiments on benchmark datasets.
In the problems of image retrieval and annotation, complete textual tag lists of images play critical roles. However, in real-world applications, the image tags are usually incomplete, thus it is important to learn the complete tags for images. In this paper, we study the problem of image tag complete and proposed a novel method for this problem based on a popular image representation method, convolutional neural network (CNN). The method estimates the complete tags from the convolutional filtering outputs of images based on a linear predictor. The CNN parameters, linear predictor, and the complete tags are learned jointly by our method. We build a minimization problem to encourage the consistency between the complete tags and the available incomplete tags, reduce the estimation error, and reduce the model complexity. An iterative algorithm is developed to solve the minimization problem. Experiments over benchmark image data sets show its effectiveness.