Semi-supervised Generative Adversarial Hashing for Image Retrieval

@inproceedings{Wang2018SemisupervisedGA,
  title={Semi-supervised Generative Adversarial Hashing for Image Retrieval},
  author={Guan'an Wang and Qinghao Hu and Jian Cheng and Zeng-Guang Hou},
  booktitle={ECCV},
  year={2018}
}
With explosive growth of image and video data on the Internet, hashing technique has been extensively studied for large-scale visual search. Benefiting from the advance of deep learning, deep hashing methods have achieved promising performance. However, those deep hashing models are usually trained with supervised information, which is rare and expensive in practice, especially class labels. In this paper, inspired by the idea of generative models and the minimax two-player game, we propose a… Expand
SSAH: Semi-supervised Adversarial Deep Hashing with Self-paced Hard Sample Generation
TLDR
A novel Semi-supervised Self-pace Adversarial Hashing method, named SSAH, to solve the above problems in a unified framework and can significantly improve state-of-the-art models on both the widely-used hashing datasets and fine-grained datasets. Expand
Anchor-Based Self-Ensembling for Semi-Supervised Deep Pairwise Hashing
TLDR
This paper proposes a novel semi-supervised deep pairwise hashing method to leverage both labeled and unlabeled data to learn hash functions and adopts self-ensembling to create strong ensemble targets for latent binary vectors of training samples and form a consensus predicting similarity relationship to multiple anchors. Expand
Generalized Product Quantization Network for Semi-supervised Hashing
TLDR
This work proposes the first quantization-based semi-supervised hashing scheme: Generalized Product Quantization (GPQ) network, which designs a novel metric learning strategy that preserves semantic similarity between labeled data, and employs entropy regularization term to fully exploit inherent potentials of unlabeled data. Expand
Scalable deep asymmetric hashing via unequal-dimensional embeddings for image similarity search
TLDR
Scalable Deep Asymmetric Hashing is an end-to-end deep hashing method based on a fast iterative optimization strategy, which utilizes two real-valued embeddings of unequal dimensions to flexibly perform asymmetric similarity computation. Expand
Classification-enhancement deep hashing for large-scale video retrieval
  • Xiushan Nie, Xin Zhou, Yang Shi, Jiande Sun, Yilong Yin
  • Computer Science
  • Appl. Soft Comput.
  • 2021
TLDR
The proposed CEDH first fuses the spatial–temporal information of videos in a deep end-to-end hashing network, and then leverages both neighborhood structure of semantics and triple similarity information to learn video hash codes. Expand
Deep Hashing with Active Pairwise Supervision
TLDR
A Deep Hashing method with Active Pairwise Supervision that achieves the accuracy of supervised hashing methods with only 30% labeled training samples and improves the semi-supervised binary codes by a sizable margin is proposed. Expand
A Novel Deep Hashing Method with Top Similarity for Image Retrieval
TLDR
A novel deep hashing model is proposed to preserve top images similar to the query images and optimize the quality of hash codes for image retrieval, utilizing the optimized AlexNet to extract discriminative image representations and learn hashing functions simultaneously. Expand
Deep multiscale divergence hashing for image retrieval
TLDR
A new deep learning to hash method, namely, deep multiscale divergence hashing, which provides a high diversity and compact image feature for image retrieval, and surpasses HashNet by 11.46%, 7.58%, and 13.86% on MS COCO, NUS-WIDE, and CIFAR-10 datasets, respectively. Expand
ExchNet: A Unified Hashing Network for Large-Scale Fine-Grained Image Retrieval
TLDR
This paper proposes a unified end-to-end trainable network, termed as ExchNet, which consistently outperforms state-of-the-art generic hashing methods on five fine-grained datasets and achieves the best speed-up and storage reduction, revealing its efficiency and practicality. Expand
Neurons Merging Layer: Towards Progressive Redundancy Reduction for Deep Supervised Hashing
TLDR
A simple yet effective Neurons Merging Layer (NMLayer) for deep supervised hashing that dynamically learned by a novel mechanism defined in the authors' active and frozen phases and outperforms state-of-the-art hashing methods. Expand
...
1
2
...

References

SHOWING 1-10 OF 37 REFERENCES
Deep Semantic Hashing with Generative Adversarial Networks
TLDR
This paper studies the exploration of generating synthetic data through semi-supervised generative adversarial networks (GANs), which leverages largely unlabeled and limited labeled training data to produce highly compelling data with intrinsic invariance and global coherence, for better understanding statistical structures of natural data. Expand
SSDH: Semi-Supervised Deep Hashing for Large Scale Image Retrieval
  • J. Zhang, Yuxin Peng
  • Computer Science
  • IEEE Transactions on Circuits and Systems for Video Technology
  • 2019
TLDR
This paper proposes a semi-supervised loss to jointly minimize the empirical error on labeled data, as well as the embedding error on both labeled and unlabeled data, which can preserve the semantic similarity and capture the meaningful neighbors on the underlying data structures for effective hashing. Expand
Semi-Supervised Deep Hashing with a Bipartite Graph
TLDR
A novel semi-supervised hashing method for image retrieval, named Deep Hashing with a Bipartite Graph (BGDH), to simultaneously learn embeddings, features and hash codes, which outperforms state-of-the-art hashing methods. Expand
Supervised hashing with kernels
TLDR
A novel kernel-based supervised hashing model which requires a limited amount of supervised information, i.e., similar and dissimilar data pairs, and a feasible training cost in achieving high quality hashing, and significantly outperforms the state-of-the-arts in searching both metric distance neighbors and semantically similar neighbors is proposed. Expand
Deep Supervised Discrete Hashing
TLDR
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. Expand
Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks
TLDR
Compared with state-of-the-art approaches, SSDH achieves higher retrieval accuracy, while the classification performance is not sacrificed; yet it is effective and outperforms other hashing approaches on several benchmarks and large datasets. 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
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
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
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
...
1
2
3
4
...