Visible to the public Deep Asymmetric Pairwise Hashing

TitleDeep Asymmetric Pairwise Hashing
Publication TypeConference Paper
Year of Publication2017
AuthorsShen, Fumin, Gao, Xin, Liu, Li, Yang, Yang, Shen, Heng Tao
Conference NameProceedings of the 2017 ACM on Multimedia Conference
Conference LocationNew York, NY, USA
ISBN Number978-1-4503-4906-2
Keywordsasymmetric hashing, binary code, compositionality, deep hashing, hash algorithms, pubcrawl, Resiliency
AbstractRecently, deep neural networks based hashing methods have greatly improved the multimedia retrieval performance by simultaneously learning feature representations and binary hash functions. Inspired by the latest advance in the asymmetric hashing scheme, in this work, we propose a novel Deep Asymmetric Pairwise Hashing approach (DAPH) for supervised hashing. The core idea is that two deep convolutional models are jointly trained such that their output codes for a pair of images can well reveal the similarity indicated by their semantic labels. A pairwise loss is elaborately designed to preserve the pairwise similarities between images as well as incorporating the independence and balance hash code learning criteria. By taking advantage of the flexibility of asymmetric hash functions, we devise an efficient alternating algorithm to optimize the asymmetric deep hash functions and high-quality binary code jointly. Experiments on three image benchmarks show that DAPH achieves the state-of-the-art performance on large-scale image retrieval.
Citation Keyshen_deep_2017