Sep 12, 2018 · Abstract: Similarity-preserving hashing is a widely used method for nearest neighbor search in large-scale image retrieval tasks.
Oct 19, 2017 · We propose a simple yet efficient deep-network-based multi-index hashing method for simultaneously learning the powerful image representation and the efficient ...
Abstract—Similarity-preserving hashing is a widely-used method for nearest neighbor search in large-scale image re- trieval tasks.
Improved Search in Hamming Space Using Deep Multi-Index Hashing
dl.acm.org › doi › TCSVT.2018.2869921
However, the binary codes generated from deep networks may be not uniformly distributed over the Hamming space, which will greatly increase the retrieval time.
Abstract—Similarity-preserving hashing is a widely-used method for nearest neighbor search in large-scale image re- trieval tasks.
We introduce a rigorous way to build multiple hash tables on binary code substrings that enables exact K-nearest neighbor search in Hamming space. The ...
Missing: Deep | Show results with:Deep
This work proposes a deep-network-based multi-index hashing (MIH) for retrieval efficiency and introduces the MIH mechanism into the proposed deep ...
To achieve these two goals, we introduce the multi-index hashing (MIH) mechanism into the proposed deep architecture, which divides the binary codes into ...
Improved Search in Hamming Space Using Deep Multi-Index Hashing. Authors. Lai, Hanjiang; Pan, Yan; Liu, Si; Weng, Zhenbin; Yin, Jian. Publication. IEEE ...
The method uses a rank-based formulation and exploits a hashing approach for efficient ranked list computation at query time. A comprehensive experimental ...