Multi-label Image Ranking based on Deep Convolutional Features

Multi-label image ranking has many important applications in the real world, and it includes two core issues: image feature extraction approach and multi-label ranking algorithm. The existing works are mainly focused on the improvement of multi-label ranking algorithm based on the conventional visual features. Recently, image features extracted from the deep convolutional neural network have achieved impressive performance for a variety of vision tasks. Using these deep features as image representations have gained more and more attention on multi-label ranking problem. In this study, we evaluate the performance of the deep features using two baseline multi-label ranking algorithms. First, the deep convolutional neural network model pre-trained on ImageNet is fine-tuned to the target dataset. Second, the global deep features of raw image are extracted from the fine-tuned model and serve as the input data of ranking algorithms. Finally, experiments using the Tasmania Coral Point Count dataset demonstrate that the deep features enhance the expression ability in comparison with that of conventional visual features, and they can effectively improve multi-label ranking performance.