Query-Adaptive Image Search with Hash Codes
Abstract
Query-Adaptive Image Search with Hash Codes.Scalable image search based on visual similarity has been an active topic of research in recent years. State-of-the-art solutions often use hashing methods to embed high-dimensional image features into Hamming space, where search can be performed in real-time based on Hamming distance of compact hash codes. Unlike traditional metrics (e.g., Euclidean) that offer continuous distances, the Hamming distances are discrete integer values. As a consequence, there are often a large number of images sharing equal Hamming distances to a query, which largely hurts search results where fine-grained ranking is very important. This paper introduces an approach that enables query-adaptive ranking of the returned images with equal Hamming distances to the queries.
Conclusion
Query-Adaptive Image Search with Hash Codes.We have presented a novel framework for query-adaptive image search with hash codes. By harnessing a large set of predefined semantic concept classes, our approach is able to predict query-adaptive bitwise weights of hash codes in real-time, with which search results can be rapidly ranked by weighted Hamming distance at finer-grained hash code level. This capability largely alleviates the effect of a coarse ranking problem that is common in hashing-based image search. Experimental results on a widely adopted Flickr image dataset confirmed the effectiveness of our proposal.
