Deep Quantization Network for Efficient Image Retrieval

Authors

  • Yue Cao Tsinghua University
  • Mingsheng Long Tsinghua University
  • Jianmin Wang Tsinghua University
  • Han Zhu Tsinghua University
  • Qingfu Wen Tsinghua University

DOI:

https://doi.org/10.1609/aaai.v30i1.10455

Keywords:

Supervised Quantization, Deep Learning, Image Retrieval

Abstract

Hashing has been widely applied to approximate nearest neighbor search for large-scale multimedia retrieval. Supervised hashing improves the quality of hash coding by exploiting the semantic similarity on data pairs and has received increasing attention recently. For most existing supervised hashing methods for image retrieval, an image is first represented as a vector of hand-crafted or machine-learned features, then quantized by a separate quantization step that generates binary codes. However, suboptimal hash coding may be produced, since the quantization error is not statistically minimized and the feature representation is not optimally compatible with the hash coding. In this paper, we propose a novel Deep Quantization Network (DQN) architecture for supervised hashing, which learns image representation for hash coding and formally control the quantization error. The DQN model constitutes four key components: (1) a sub-network with multiple convolution-pooling layers to capture deep image representations; (2) a fully connected bottleneck layer to generate dimension-reduced representation optimal for hash coding; (3) a pairwise cosine loss layer for similarity-preserving learning; and (4) a product quantization loss for controlling hashing quality and the quantizability of bottleneck representation. Extensive experiments on standard image retrieval datasets show the proposed DQN model yields substantial boosts over latest state-of-the-art hashing methods.

Downloads

Published

2016-03-05

How to Cite

Cao, Y., Long, M., Wang, J., Zhu, H., & Wen, Q. (2016). Deep Quantization Network for Efficient Image Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence, 30(1). https://doi.org/10.1609/aaai.v30i1.10455