Corpus ID: 58007011

Deep Supervised Hashing leveraging Quadratic Spherical Mutual Information for Content-based Image Retrieval

  title={Deep Supervised Hashing leveraging Quadratic Spherical Mutual Information for Content-based Image Retrieval},
  author={Nikolaos Passalis and Anastasios Tefas},
Several deep supervised hashing techniques have been proposed to allow for efficiently querying large image databases. However, deep supervised image hashing techniques are developed, to a great extent, heuristically often leading to suboptimal results. Contrary to this, we propose an efficient deep supervised hashing algorithm that optimizes the learned codes using an information-theoretic measure, the Quadratic Mutual Information (QMI). The proposed method is adapted to the needs of large… 
1 Citations
Perceptual hashing for image authentication: A survey
In this article, the general structure and classifications of image hashing based tamper detection techniques with their properties are exploited and the evaluation datasets and different performance metrics are discussed.


Deep Hashing Network for Efficient Similarity Retrieval
A novel Deep Hashing Network (DHN) architecture for supervised hashing is proposed, in which good image representation tailored to hash coding and formally control the quantization error are jointly learned.
Deep Asymmetric Pairwise Hashing
This work proposes a novel Deep Asymmetric Pairwise Hashing approach (DAPH) for supervised hashing, and devise an efficient alternating algorithm to optimize the asymmetric deep hash functions and high-quality binary code jointly.
Hashing with dual complementary projection learning for fast image retrieval
A novel dual complementary hashing (DCH) approach to learn the codes with multiple hash tables so that the binary codes learned by this approach are more powerful for fast similarity search.
Deep Supervised Discrete Hashing
This paper develops a deep supervised discrete hashing algorithm based on the assumption that the learned binary codes should be ideal for classification, which outperforms current state-of-the-art methods on benchmark datasets.
Feature Learning Based Deep Supervised Hashing with Pairwise Labels
Experiments show that the proposed deep pairwise-supervised hashing method (DPSH), to perform simultaneous feature learning and hashcode learning for applications with pairwise labels, can outperform other methods to achieve the state-of-the-art performance in image retrieval applications.
Deep Supervised Hashing with Triplet Labels
A triplet label based deep hashing method which aims to maximize the likelihood of the given triplet labels, which outperforms all the baselines on CIFAR-10 and NUS-WIDE datasets, including the state-of-the-art method DPSH.
Deep semantic ranking based hashing for multi-label image retrieval
  • F. Zhao, Y. Huang, Liang Wang, T. Tan
  • Computer Science, Mathematics
    2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
In this work, deep convolutional neural network is incorporated into hash functions to jointly learn feature representations and mappings from them to hash codes, which avoids the limitation of semantic representation power of hand-crafted features.
Supervised Hashing for Image Retrieval via Image Representation Learning
Extensive empirical evaluations on three benchmark datasets with different kinds of images show that the proposed method has superior performance gains over several state-of-the-art supervised and unsupervised hashing methods.
Semi-supervised spectral hashing for fast similarity search
A novel semi-supervised hashing method to take into account the pairwise supervised information including must-link and cannot-link, and then maximize the information provided by each bit according to both the labeled data and the unlabeled data is proposed.
Deep Supervised Hashing for Fast Image Retrieval
A novel Deep Supervised Hashing method to learn compact similarity-preserving binary code for the huge body of image data using pairs/triplets of images as training inputs and encouraging the output of each image to approximate discrete values.