Dual Purpose Hashing
Haomiao Liu, Ruiping Wang, Shiguang Shan, Xilin Chen

TL;DR
This paper introduces Dual Purpose Hashing (DPH), a CNN-based method that efficiently captures both category and attribute similarities for image retrieval, leveraging partially labeled data to outperform specialized methods.
Contribution
The novel DPH method jointly preserves category and attribute similarities using CNNs and handles partially labeled data, enabling efficient dual-purpose image retrieval.
Findings
Achieves comparable or better performance than state-of-the-art methods.
Produces more compact hash codes.
Effectively utilizes partially labeled data.
Abstract
Recent years have seen more and more demand for a unified framework to address multiple realistic image retrieval tasks concerning both category and attributes. Considering the scale of modern datasets, hashing is favorable for its low complexity. However, most existing hashing methods are designed to preserve one single kind of similarity, thus improper for dealing with the different tasks simultaneously. To overcome this limitation, we propose a new hashing method, named Dual Purpose Hashing (DPH), which jointly preserves the category and attribute similarities by exploiting the Convolutional Neural Network (CNN) models to hierarchically capture the correlations between category and attributes. Since images with both category and attribute labels are scarce, our method is designed to take the abundant partially labelled images on the Internet as training inputs. With such a framework,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Image and Video Retrieval Techniques · Image Retrieval and Classification Techniques · Multimodal Machine Learning Applications
