| In recent years,social networking sites such as Flickr,Facebook and Sina Weibo have been gradually emerging.Heterogeneous data such as images,videos,audio and texts have grown at an alarming rate every day.How to search and retrieve the images that users need or are interested in conveniently,quickly and accurately in these vast image databases has become a hot topic in the field of multimedia information retrieval.Image retrieval based on deep hashing methods has attracted more and more attentions from both academic and industry,due to the out-standing performance of deep neural network in various tasks of computer vision.However,most of the hashing methods are designed to learn simple similarity only for single-label image retrieval,thus cannot work well for the multi-label cases.In this paper,we proposed a framework named Deep Multi-Similarity Hashing(DMSH)method to learn semantic binary representations for multi-label image retrieval task.In the proposed model,a convolutional architecture is incorporated with hash function to learn compact binary representations from every pair of images with multiple labels.On the purposed of learning semantic structure of multi-label images,we define the pairwise loss for multi-label image pairs,which is influenced by zero-loss interval under the control of the number of common labels.For certain image pair with many common labels,its zero-loss interval is small relatively and the distance of their output of network affect total loss more.Therefore,convolutional neural network will pay more attention to high-level similar image pair than low-level similar image pair during the training process.Furthermore,our proposed model is flexible to be implemented with various deep networks.Experiments on large scale dataset NUS-WIDE have proved the state-of-the-art performance of our proposed DMSH model in the task of multi-label image retrieval. |
