Exploring image specific structured loss for image annotation with incomplete labelling

In this paper, we address the problem of image annotation with incomplete labelling, where the multiple objects in each training image are not fully labeled. The conventional one-versus-all SVM (OVA-SVM) that performs fairly well on full labelling decays drastically under the incomplete setting. Recently, structured learning method termed OVA-SSVM is proposed to boost the performance of OVA-SVM by modeling the structured associations of labels and show efficiency under incomplete setting. The OVA-SSVM assumes that each training sample includes a single label and adopts an loss measure of classification style that as long as one of the predicted label is correct, the overall prediction should be considered correct. However, this may not be appropriate for the multi-label annotation task. In this paper, we extend the OVA-SSVM method to the multi-label situation and design a novel image specific structured loss measure to account for the dependencies between predicted labels relying on the image-label associations. Then we develop an efficient optimization algorithm to learn the model parameters. Finally, we present extensive empirical results on two benchmark datasets with various degree of incompletion, and show that proposed method outperforms OVA-SSVM and achieves competitive performance compared with other state-of-the-art methods which are also designed for the issue of incomplete labelling.