Unsupervised Semantic Deep Hashing
This addresses the challenge of time-consuming image annotation in real-world applications by providing an unsupervised method for image retrieval, though it appears incremental as it builds on existing deep hashing techniques.
The paper tackles the problem of unsupervised hashing for large-scale image retrieval by proposing USDH, which uses semantic information from CNN features to guide training and enforces four criteria on hashing codes. The result is that USDH outperforms state-of-the-art unsupervised methods on datasets like CIFAR-10 and NUSWIDE, with experiments also showing efficiency for fine-grained classification on Oxford 17.
In recent years, deep hashing methods have been proved to be efficient since it employs convolutional neural network to learn features and hashing codes simultaneously. However, these methods are mostly supervised. In real-world application, it is a time-consuming and overloaded task for annotating a large number of images. In this paper, we propose a novel unsupervised deep hashing method for large-scale image retrieval. Our method, namely unsupervised semantic deep hashing (\textbf{USDH}), uses semantic information preserved in the CNN feature layer to guide the training of network. We enforce four criteria on hashing codes learning based on VGG-19 model: 1) preserving relevant information of feature space in hashing space; 2) minimizing quantization loss between binary-like codes and hashing codes; 3) improving the usage of each bit in hashing codes by using maximum information entropy, and 4) invariant to image rotation. Extensive experiments on CIFAR-10, NUSWIDE have demonstrated that \textbf{USDH} outperforms several state-of-the-art unsupervised hashing methods for image retrieval. We also conduct experiments on Oxford 17 datasets for fine-grained classification to verify its efficiency for other computer vision tasks.