This article targets fully supervised image classification and few-shot image classification in an unified way by decomposing visual and semantic correlations. The intrinsic correlations of visual and semantic information of the same class are jointly modeled. We decompose visual and semantic correlations using low-rank and sparse constraints. The decomposed parts character the intrinsic correlations of images. Classification can then be conducted by reconstruction error minimization. Extensive experiments on several datasets well prove the effectiveness of the proposed method.

Most image classification methods are designed to either boost the classification accuracies with abundant supervision, or cope with the shortage of supervision information. This is often achieved by using the visual and semantic information of other sources. However, these methods use the visual and semantic information within the same class independently, leaving their intrinsic correlations unconsidered. Objects and disturbing components as well as noise exist on the same image. Besides, semantic representations also contain noisy information. To solve the problems mentioned above, we propose a novel method for both fully supervised image classification and few-shot image classification by decomposing visual and semantic correlations. We jointly explore the intrinsic correlations of visual and semantic information of images within the same class. For each class, we decompose its visual and semantic correlations using low-rank and sparse constraint respectively. The decomposed low-ra...