Issue No. 12 - Dec. (2018 vol. 40)
Fumin Shen , University of Electronic Science and Technology of China, Chengdu, Sichuan, China
Yan Xu , University of Electronic Science and Technology of China, Chengdu, Sichuan, China
Li Liu , University of East Anglia, Norwich, United Kingdom
Yang Yang , University of Electronic Science and Technology of China, Chengdu, Sichuan, China
Zi Huang , The University of Queensland, St Lucia, Queensland, Australia
Heng Tao Shen , University of Electronic Science and Technology of China, Chengdu, Sichuan, China
Recent vision and learning studies show that learning compact hash codes can facilitate massive data processing with significantly reduced storage and computation. Particularly, learning deep hash functions has greatly improved the retrieval performance, typically under the semantic supervision. In contrast, current unsupervised deep hashing algorithms can hardly achieve satisfactory performance due to either the relaxed optimization or absence of similarity-sensitive objective. In this work, we propose a simple yet effective unsupervised hashing framework, named Similarity-Adaptive Deep Hashing (SADH), which alternatingly proceeds over three training modules: deep hash model training, similarity graph updating and binary code optimization. The key difference from the widely-used two-step hashing method is that the output representations of the learned deep model help update the similarity graph matrix, which is then used to improve the subsequent code optimization. In addition, for producing high-quality binary codes, we devise an effective discrete optimization algorithm which can directly handle the binary constraints with a general hashing loss. Extensive experiments validate the efficacy of SADH, which consistently outperforms the state-of-the-arts by large gaps.
Binary codes, Optimization, Image retrieval, Quantization (signal), Adaptation models, Data models, Semantics, Unsupervised learning
F. Shen, Y. Xu, L. Liu, Y. Yang, Z. Huang and H. T. Shen, "Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 40, no. 12, pp. 3034-3044, 2018.