Object Detection based Deep Unsupervised Hashing
This work addresses the challenge of enhancing image retrieval efficiency for unlabeled data, representing an incremental improvement over existing unsupervised hashing methods.
The paper tackles the problem of improving unsupervised hashing for large-scale image retrieval by mining supervised semantic label information from unlabeled data using a pre-trained object detection model, and demonstrates that the proposed method outperforms state-of-the-art unsupervised hashing methods on two public datasets.
Recently, similarity-preserving hashing methods have been extensively studied for large-scale image retrieval. Compared with unsupervised hashing, supervised hashing methods for labeled data have usually better performance by utilizing semantic label information. Intuitively, for unlabeled data, it will improve the performance of unsupervised hashing methods if we can first mine some supervised semantic 'label information' from unlabeled data and then incorporate the 'label information' into the training process. Thus, in this paper, we propose a novel Object Detection based Deep Unsupervised Hashing method (ODDUH). Specifically, a pre-trained object detection model is utilized to mining supervised 'label information', which is used to guide the learning process to generate high-quality hash codes.Extensive experiments on two public datasets demonstrate that the proposed method outperforms the state-of-the-art unsupervised hashing methods in the image retrieval task.