Random attributes for image classification

Previous studies have shown that attribute based approaches obtained successful results in image classification. However, in human based supervised methods, it gets harder to determine all the attributes, which are associated with image classes, in large datasets. In addition, human beings have difficulties in characterizing discriminative attributes among images. In unsupervised methods, when the number of classes increases, the excessive growth of the search space appears to be a major problem. In this study, we try to solve the problems in supervised and unsupervised methods by random attribute approach. Random attributes can be defined as hypothetical attributes which depict images. They are extracted randomly from the feature space as binary or relative. The proposed approach has been compared to the other attribute based studies in the literature using the same data sets. The highest image classification performances obtained in other studies has been reached in the experiments especially as the number of attributes increase.