Pseudo Label based Unsupervised Deep Discriminative Hashing for Image Retrieval

@article{Hu2017PseudoLB,
  title={Pseudo Label based Unsupervised Deep Discriminative Hashing for Image Retrieval},
  author={Qinghao Hu and Jiaxiang Wu and Jian Cheng and Lifang Wu and Hanqing Lu},
  journal={Proceedings of the 25th ACM international conference on Multimedia},
  year={2017}
}
Hashing methods play an important role in large scale image retrieval. Traditional hashing methods use hand-crafted features to learn hash functions, which can not capture the high level semantic information. Deep hashing algorithms use deep neural networks to learn feature representation and hash functions simultaneously. Most of these algorithms exploit supervised information to train the deep network. However, supervised information is expensive to obtain. In this paper, we propose a pseudo… Expand
Discriminative deep metric learning for asymmetric discrete hashing
TLDR
A novel discriminative deep metric learning approach for asymmetric discrete hashing (ADMH) approach for supervised hashing learning and extensive experiments show that the proposed asymmetric deep hashing method outperforms the existing hashing methods. Expand
Deep supervised hashing using symmetric relative entropy
TLDR
This work proposes a novel deep supervised hashing method that aims to minimize the information loss generated during the embedding process, measured by the Jensen–Shannon divergence to ensure that compact hash codes have a similar distribution with those from the original images. Expand
Clustering-driven unsupervised deep hashing for image retrieval
TLDR
A novel end-to-end deep framework for image retrieval, namely Clustering-driven Unsupervised Deep Hashing (CUDH), to recursively learn discriminative clusters by soft clustering model and produce binary code with high similarity responds is proposed. Expand
Efficient inter-image relation graph neural network hashing for scalable image retrieval
TLDR
This paper proposes a simple but effective Inter-image Relation Graph Neural Network Hashing (IRGNNH) method, which significantly outperforms the state-of-the-art unsupervised deep hashing methods on both retrieval accuracy and efficiency. Expand
Deep Unsupervised Hashing by Distilled Smooth Guidance
TLDR
A novel deep unsupervised hashing method, namely Distilled Smooth Guidance (DSG), which can learn a distilled dataset consisting of similarity signals as well as smooth confidence signals and construct a priority loss function for smooth similarity-preserving learning. Expand
Unsupervised Deep Quadruplet Hashing with Isometric Quantization for image retrieval
TLDR
A novel unsupervised deep hashing framework to learn compact binary codes, which takes the quadruplet forms as input units, called Unsupervised Deep Quadruplet Hashing with Isometric Quantization (UDQH-IQ), which achieves promising performance. Expand
Two-pronged Strategy: Lightweight Augmented Graph Network Hashing for Scalable Image Retrieval
  • Hui Cui, Lei Zhu, Jingjing Li, Zhiyong Cheng, Zheng Zhang
  • Computer Science
  • ArXiv
  • 2021
TLDR
This paper proposes a simple and efficient Lightweight Augmented Graph Network Hashing (LAGNH) method with a twopronged strategy, which achieves significant performance improvement compared with the state-of-the-art unsupervised deep hashing methods in terms of both retrieval accuracy and efficiency. Expand
Contrastive Self-Supervised Hashing With Dual Pseudo Agreement
TLDR
This work uses the refined pseudo labels as a stabilization constraint to train hash codes, which can implicitly encode semantic structures of the data into the learned Hamming space and can consistently outperform state-of-the-art methods by large margins. Expand
A Two-Step Cross-Modal Hashing by Exploiting Label Correlations and Preserving Similarity in Both Steps
TLDR
To the best of the knowledge, this paper is the first cross-modal hashing method exploiting label correlations, and also the first two-step hashing model preserving the similarity while leaning hash function. Expand
Neighborhood Pyramid Preserving Hashing
TLDR
The proposed Neighbourhood Pyramid preserving Hashing method achieves stricter neighbourhood structure preserving over previous graph hashing algorithms and achieves promising performances compared with those of the existing state-of-the-art unsupervised binary hashing methods. Expand
...
1
2
...

References

SHOWING 1-10 OF 28 REFERENCES
Feature Learning Based Deep Supervised Hashing with Pairwise Labels
TLDR
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. Expand
Deep Hashing Network for Efficient Similarity Retrieval
TLDR
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. Expand
Supervised Hashing for Image Retrieval via Image Representation Learning
TLDR
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. Expand
Simultaneous feature learning and hash coding with deep neural networks
TLDR
Extensive evaluations on several benchmark image datasets show that the proposed simultaneous feature learning and hash coding pipeline brings substantial improvements over other state-of-the-art supervised or unsupervised hashing methods. Expand
Deep Supervised Hashing for Fast Image Retrieval
TLDR
A novel Deep Supervised Hashing method to learn compact similarity-preserving binary code for the huge body of image data and extensive experiments show the promising performance of the method compared with the state-of-the-arts. Expand
Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks
TLDR
Experimental results on three different visual analysis tasks including image matching, image retrieval, and object recognition clearly demonstrate the effectiveness of the proposed unsupervised deep learning approach called DeepBit. Expand
Learning to Hash with Binary Reconstructive Embeddings
TLDR
An algorithm for learning hash functions based on explicitly minimizing the reconstruction error between the original distances and the Hamming distances of the corresponding binary embeddings is developed. Expand
Scalable Graph Hashing with Feature Transformation
TLDR
A novel method, called scalable graph hashing with feature transformation (SGH), for large-scale graph hashing that can effectively approximate the whole graph without explicitly computing the similarity graph matrix, based on which a sequential learning method is proposed to learn the hash functions in a bitwise manner. Expand
Deep hashing for compact binary codes learning
TLDR
A deep neural network is developed to seek multiple hierarchical non-linear transformations to learn compact binary codes for large scale visual search and shows the superiority of the proposed approach over the state-of-the-arts. Expand
Efficient Training of Very Deep Neural Networks for Supervised Hashing
TLDR
This paper proposes a novel and efficient training algorithm inspired by alternating direction method of multipliers (ADMM) that overcomes some of the limitations of existing methods for supervised learning of hash codes. Expand
...
1
2
3
...