Filters








2,051 Hits in 3.0 sec

Deep Semantic Hashing with Generative Adversarial Networks [article]

Zhaofan Qiu and Yingwei Pan and Ting Yao and Tao Mei
2018 arXiv   pre-print
Specifically, a novel deep semantic hashing with GANs (DSH-GANs) is presented, which mainly consists of four components: a deep convolution neural networks (CNN) for learning image representations, an  ...  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  ...  (8) Deep Semantic Hashing with Generative Adversarial Networks (DSH-GANs) is our proposal in this paper.  ... 
arXiv:1804.08275v1 fatcat:y5jiqkg2mbhd3nzeuxvfzc4lsq

Deep Semantic Hashing with Generative Adversarial Networks

Zhaofan Qiu, Yingwei Pan, Ting Yao, Tao Mei
2017 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '17  
Specifically, a novel deep semantic hashing with GANs (DSH-GANs) is presented, which mainly consists of four components: a deep convolution neural networks (CNN) for learning image representations, an  ...  This paper studies the exploration of generating synthetic data through semisupervised generative adversarial networks (GANs), which leverages largely unlabeled and limited labeled training data to produce  ...  (8) Deep Semantic Hashing with Generative Adversarial Networks (DSH-GANs) is our proposal in this paper.  ... 
doi:10.1145/3077136.3080842 dblp:conf/sigir/QiuPYM17 fatcat:h5jc4hkgeng5rnhbzu6gou4f3e

Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing [article]

Xunguang Wang, Zheng Zhang, Baoyuan Wu, Fumin Shen, Guangming Lu
2021 arXiv   pre-print
To the best of our knowledge, this is the first generation-based method to attack deep hashing networks.  ...  However, deep hashing networks are vulnerable to adversarial examples, which is a practical secure problem but seldom studied in hashing-based retrieval field.  ...  network to generate semantically preserved hash codes.  ... 
arXiv:2105.07553v1 fatcat:2y6tg2vsrnd35afb7ylbsl23hi

Semi-supervised Generative Adversarial Hashing for Image Retrieval [chapter]

Guan'an Wang, Qinghao Hu, Jian Cheng, Zengguang Hou
2018 Lecture Notes in Computer Science  
In this paper, inspired by the idea of generative models and the minimax two-player game, we propose a novel semi-supervised generative adversarial hashing (SSGAH) approach.  ...  However, those deep hashing models are usually trained with supervised information, which is rare and expensive in practice, especially class labels.  ...  Deep Semantic Hashing with GANs (DSH-GANs) [21] minimizes the empirical error over synthetic data generated conditioned on class labels based on deep architecture.  ... 
doi:10.1007/978-3-030-01267-0_29 fatcat:tczbtvxjsjcixheybhrdgclyve

Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion [article]

Yang Wang
2020 arXiv   pre-print
Recently, deep neural networks have exhibited as a powerful architecture to well capture the nonlinear distribution of high-dimensional multimedia data, so naturally does for multi-modal data.  ...  Throughout this survey, we further indicate that the critical components for this field go to collaboration, adversarial competition and fusion over multi-modal spaces.  ...  [151] developed a novel deep hashing approach, termed as Multi-Task Consistency Preserving Adversarial Hashing (CPAH), to capture cross-modal semantic correlation.  ... 
arXiv:2006.08159v1 fatcat:g4467zmutndglmy35n3eyfwxku

Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval [article]

Chao Li and Cheng Deng and Ning Li and Wei Liu and Xinbo Gao and Dacheng Tao
2018 arXiv   pre-print
In this paper, we propose a self-supervised adversarial hashing (SSAH) approach, which lies among the early attempts to incorporate adversarial learning into cross-modal hashing in a self-supervised fashion  ...  The primary contribution of this work is that two adversarial networks are leveraged to maximize the semantic correlation and consistency of the representations between different modalities.  ...  In the first phase, modality-specific features from separate generator networks are associated with each other in a common semantic space.  ... 
arXiv:1804.01223v1 fatcat:k76qsfqyzba7deegi5ag7l5fcu

Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval

Chao Li, Cheng Deng, Ning Li, Wei Liu, Xinbo Gao, Dacheng Tao
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
In this paper, we propose a self-supervised adversarial hashing (SSAH) approach, which lies among the early attempts to incorporate adversarial learning into cross-modal hashing in a self-supervised fashion  ...  The primary contribution of this work is that two adversarial networks are leveraged to maximize the semantic correlation and consistency of the representations between different modalities.  ...  This may be because two adversarial networks are used in our framework, with which SSAH can more Conclusion In this work, we proposed a novel deep hashing approach, dubbed self-supervised adversarial  ... 
doi:10.1109/cvpr.2018.00446 dblp:conf/cvpr/LiDL0GT18 fatcat:btx7fqba2raejio3txomwed3zi

Progressive Generative Hashing for Image Retrieval

Yuqing Ma, Yue He, Fan Ding, Sheng Hu, Jun Li, Xianglong Liu
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
generative adversarial networks (GANs).  ...  However, without semantic label information, the unsupervised deep hashing still remains an open question.  ...  To exhaustively exploit the power of GAN itself, this paper proposes a novel progressive generative adversarial frame- work to help learn a discriminative deep hashing network in an unsupervised way.  ... 
doi:10.24963/ijcai.2018/121 dblp:conf/ijcai/MaHDHLL18 fatcat:fgl24i644bdyfh37wl37dhsfxq

Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval

Lin Wu, Yang Wang, Ling Shao
2019 IEEE Transactions on Image Processing  
To induce the hash codes with semantics to the input-output pair, cycle consistency loss is further proposed upon the adversarial training to strengthen the correlations between inputs and corresponding  ...  In this paper, we propose a novel deep generative approach to cross-modal retrieval to learn hash functions in the absence of paired training samples through the cycle consistency loss.  ...  Generative Adversarial Networks Recently, generative adversarial networks (GANs) have been proposed to estimate a generative model by an adversarial training process [26] , and GANs-based networks can  ... 
doi:10.1109/tip.2018.2878970 fatcat:oy33fwr4mje5fd2njqzmioeq2a

SSAH: Semi-supervised Adversarial Deep Hashing with Self-paced Hard Sample Generation [article]

Sheng Jin, Shangchen Zhou, Yao Liu, Chao Chen, Xiaoshuai Sun, Hongxun Yao, Xiansheng Hua
2019 arXiv   pre-print
The SSAH method consists of an adversarial network (A-Net) and a hashing network (H-Net).  ...  The current solutions to this issue utilize Generative Adversarial Network (GAN) to augment data in semi-supervised learning.  ...  Compared with traditional ones, deep hashing methods usually Figure 1 : To obtain the optimal boundary for points with similar hashing codes, we propose a novel self-paced deep adversarial hashing to  ... 
arXiv:1911.08688v1 fatcat:4gachgfntbaq5kzplq2e57yxce

SSAH: Semi-Supervised Adversarial Deep Hashing with Self-Paced Hard Sample Generation

Sheng Jin, Shangchen Zhou, Yao Liu, Chao Chen, Xiaoshuai Sun, Hongxun Yao, Xian-Sheng Hua
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
The SSAH method consists of an adversarial network (A-Net) and a hashing network (H-Net).  ...  The current solutions to this issue utilize Generative Adversarial Network (GAN) to augment data in semi-supervised learning.  ...  Compared with traditional ones, deep hashing methods usually achieve better re- Figure 1 : To obtain the optimal boundary for points with similar hashing codes, we propose a novel self-paced deep adversarial  ... 
doi:10.1609/aaai.v34i07.6773 fatcat:gpnysdgguffezmo2wsagypl2ya

A Decade Survey of Content Based Image Retrieval using Deep Learning [article]

Shiv Ram Dubey
2020 arXiv   pre-print
Generally, the similarity between the representative features of the query image and dataset images is used to rank the images for retrieval.  ...  The taxonomy used in this survey covers different supervision, different networks, different descriptor type and different retrieval type.  ...  A semi-supervised self-pace adversarial hashing (SSAH) method is discovered in [117] by integrating an adversarial network (ANet) with a hashing network (H-Net).  ... 
arXiv:2012.00641v1 fatcat:2zcho2szpzcc3cs6uou3jpcley

TUCH: Turning Cross-view Hashing into Single-view Hashing via Generative Adversarial Nets

Xin Zhao, Guiguang Ding, Yuchen Guo, Jungong Han, Yue Gao
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
TUCH is a novel deep architecture that integrates a language model network T for text feature extraction, a generator network G to generate fake images from text feature and a hashing network H for learning  ...  Our architecture effectively unifies joint generative adversarial learning and cross-view hashing.  ...  Generator network and discriminative sub-network constitute a normal conditional GANs. Semantic hashing sub-network is a normal image hashing network based on CNN.  ... 
doi:10.24963/ijcai.2017/491 dblp:conf/ijcai/ZhaoDGHG17 fatcat:ajwn5xn4ejhqrpk7q3633eo5dm

SCH-GAN: Semi-supervised Cross-modal Hashing by Generative Adversarial Network [article]

Jian Zhang, Yuxin Peng, Mingkuan Yuan
2018 arXiv   pre-print
The main contributions can be summarized as follows: (1) We propose a novel generative adversarial network for cross-modal hashing.  ...  To address these problems, in this paper we propose a novel Semi-supervised Cross-Modal Hashing approach by Generative Adversarial Network (SCH-GAN).  ...  Generative Adversarial Network Generative Adversarial Network (GAN) [29] is first proposed to estimate generative model by an adversarial process.  ... 
arXiv:1802.02488v1 fatcat:3zxx64d7eza6xk6gt4rkmyb4vq

Deep Multi-level Semantic Hashing for Cross-modal Retrieval

Zhenyan Ji, Weina Yao, Wei Wei, Houbing Song, Huaiyu Pi
2019 IEEE Access  
In this paper, the multi-level semantic supervision generating approach is proposed by exploring the label relevance.  ...  INDEX TERMS Cross-modal retrieval, deep learning, hashing method, multi-label learning.  ...  They proposed to use semi-supervised hashing approach by generative adversarial network.  ... 
doi:10.1109/access.2019.2899536 fatcat:xynopqlgyfhe3ef6su55zqczim
« Previous Showing results 1 — 15 out of 2,051 results