Filters








6,480 Hits in 2.4 sec

Deep Residual Hashing [article]

Sailesh Conjeti, Abhijit Guha Roy, Amin Katouzian, Nassir Navab
2016 arXiv   pre-print
In this paper, for the first time, we propose a deep architecture for supervised hashing through residual learning, termed Deep Residual Hashing (DRH), for an end-to-end simultaneous representation learning  ...  The DRH model constitutes four key elements: (1) a sub-network with multiple stacked residual blocks; (2) hashing layer for binarization; (3) supervised retrieval loss function based on neighbourhood component  ...  learning based hashing approach leveraging upon residual learning, termed as Deep Residual Hashing (DRH).  ... 
arXiv:1612.05400v1 fatcat:5gao7f3vqzcn5cvwv2jn4snzki

Cross-Model Hashing Retrieval Based on Deep Residual Network

Zhiyi Li, Xiaomian Xu, Du Zhang, Peng Zhang
2021 Computer systems science and engineering  
This paper proposes a new solution to the problem of feature extraction and unified mapping of different modes: A Cross-Modal Hashing retrieval algorithm based on Deep Residual Network (CMHR-DRN).  ...  The model construction is divided into two stages: The first stage is the feature extraction of different modal data, including the use of Deep Residual Network (DRN) to extract the image features, using  ...  Retrieval algorithm based on Deep Residual Network (CMHR-DRN).  ... 
doi:10.32604/csse.2021.014563 fatcat:maw3votu7bdl5csccvqniby65i

Cohesion Intensive Deep Hashing for Remote Sensing Image Retrieval

Lirong Han, Peng Li, Xiao Bai, Christos Grecos, Xiaoyu Zhang, Peng Ren
2019 Remote Sensing  
In this scenario, the representational power of the residual net architecture is exploited to establish an end-to-end deep hashing model.  ...  In order to improve hashing performance, we develop a cohesion intensive deep hashing model for remote sensing image retrieval.  ...  Residual Hash Net We present a deep net architecture for generating remote sensing image hash codes.  ... 
doi:10.3390/rs12010101 fatcat:ybk53dksjfdxpewqw4bsxaok7q

An Adaptive and Asymmetric Residual Hash for Fast Image Retrieval

Shuli Cheng, Liejun Wang, Anyu Du
2019 IEEE Access  
INDEX TERMS Residual hash, asymmetric manner, adaptive and asymmetric residual hash (AASH), information search, hash coding. 78942 2169-3536  ...  The experimental results on three different datasets fully demonstrate that the proposed AASH method has better performance than most symmetric and asymmetric deep hash algorithms.  ...  In short, an adaptive and asymmetric deep hash algorithm was proposed based on residual network, integrated network and hash method.  ... 
doi:10.1109/access.2019.2922738 fatcat:52ogkqovwjgrfkdj54wweu5gbq

Large-Scale Remote Sensing Image Retrieval Based on Semi-Supervised Adversarial Hashing

Xu Tang, Chao Liu, Jingjing Ma, Xiangrong Zhang, Fang Liu, Licheng Jiao
2019 Remote Sensing  
First, a residual auto-encoder (RAE) is developed to generate the class variable and hash code.  ...  In this paper, we propose a new hash learning method, named semi-supervised deep adversarial hashing (SDAH), to accomplish the ANN for the large-scale RSIR task.  ...  Deep supervised discrete hashing.  ... 
doi:10.3390/rs11172055 fatcat:cy3ehjr2ejf7dezr4j4idc4jra

Histopathological Image Retrieval Based on Asymmetric Residual Hash and DNA Coding

Shuli Cheng, Liejun Wang, Anyu Du
2019 IEEE Access  
INDEX TERMS Histopathological image retrieval, asymmetric residual hash, computer-aided diagnosis, patient privacy, DNA coding.  ...  In order to further improve the effectiveness and safety of histopathological image retrieval, this paper proposes a new histopathological retrieval scheme based on asymmetric residual hash (ARH) and DNA  ...  On one hand, in order to further improve the retrieval effect of CAD system, this paper focuses on the deep residual hash algorithm to improve the accuracy and real-time of pathological image retrieval  ... 
doi:10.1109/access.2019.2930177 fatcat:4abayq3lyfdm3gulgk4zji3ffe

Hashing with Binary Matrix Pursuit [chapter]

Fatih Cakir, Kun He, Stan Sclaroff
2018 Lecture Notes in Computer Science  
We first provide a theoretical analysis on the quality of the binary codes and show that, under mild assumptions, a residual learning scheme can construct binary codes that fit any neighborhood structure  ...  We propose theoretical and empirical improvements for twostage hashing methods.  ...  Deep-learning based hashing methods such as DPSH, DTSH and MIHash outperform most non-deep hashing solutions.  ... 
doi:10.1007/978-3-030-01228-1_21 fatcat:mhaeamzhaneq3lywkpgl5dawvq

Hashing with Binary Matrix Pursuit [article]

Fatih Cakir, Kun He, Stan Sclaroff
2018 arXiv   pre-print
We first provide a theoretical analysis on the quality of the binary codes and show that, under mild assumptions, a residual learning scheme can construct binary codes that fit any neighborhood structure  ...  We propose theoretical and empirical improvements for two-stage hashing methods.  ...  Deep-learning based hashing methods such as DPSH, DTSH and MIHash outperform most non-deep hashing solutions.  ... 
arXiv:1808.01990v1 fatcat:lpembrsfqjhf7kci5sihy23usu

Deep Hashing Network for Efficient Similarity Retrieval

Han Zhu, Mingsheng Long, Jianmin Wang, Yue Cao
2016 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this paper, we propose a novel Deep Hashing Network (DHN) architecture for supervised hashing, in which we jointly learn good image representation tailored to hash coding and formally control the quantization  ...  Supervised hashing, which improves the quality of hash coding by exploiting the semantic similarity on data pairs, has received increasing attention recently.  ...  Therefore, suboptimal hash coding may be produced by existing deep hashing methods.  ... 
doi:10.1609/aaai.v30i1.10235 fatcat:psdydatnujbo7lqeiii63atsbq

Ornament Image Retrieval Using Multimodal Fusion

Sk Maidul Islam, Subhankar Joardar, Debi Prosad Dogra, Arif Ahmed Sekh
2021 SN Computer Science  
We have used four different methods namely hash-based, histogram-based, deep feature comparison, and feature cross correlation to find the similarity.  ...  To extract the similarity among images in an unsupervised manner, we have used (1) PD = p ∑ i,j=1 min(D(I i , I j )). (2) D = {d deep , d histogram , d correlation , d hash }. residual-based deep neural  ...  Deep residual similarity Deep learning is one of the most powerful tools in the computer vision community and it became the state-of-the-art in image processing.  ... 
doi:10.1007/s42979-021-00734-1 fatcat:6qtpsxax6rcbdgdr4voyifco3u

Deep Visual-Semantic Hashing for Cross-Modal Retrieval

Yue Cao, Mingsheng Long, Jianmin Wang, Qiang Yang, Philip S. Yu
2016 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16  
This paper presents a new Deep Visual-Semantic Hashing (DVSH) model that generates compact hash codes of images and sentences in an end-to-end deep learning architecture, which capture the intrinsic cross-modal  ...  DVSH is a hybrid deep architecture that constitutes a visualsemantic fusion network for learning joint embedding space of images and text sentences, and two modality-specific hashing networks for learning  ...  The residuals in all layers can be computed by back-propagation. For the hashing networks, we derive the gradient of pointwise loss Oi w.r.t.  ... 
doi:10.1145/2939672.2939812 dblp:conf/kdd/CaoLWYY16 fatcat:yw3a37355rbrzjg6qkh2nvwq5q

Context Unaware Knowledge Distillation for Image Retrieval [article]

Bytasandram Yaswanth Reddy, Shiv Ram Dubey, Rakesh Kumar Sanodiya, Ravi Ranjan Prasad Karn
2022 arXiv   pre-print
cauchy hashing (DCH) and central similarity quantization (CSQ).  ...  Existing data-dependent hashing methods use large backbone networks with millions of parameters and are computationally complex.  ...  ResNet Overview The building block of ResNet is the residual block which is one of the significant advancements in deep learning.  ... 
arXiv:2207.09070v1 fatcat:wx62pqrwfjamjps6hen2yvnhm4

Vision Transformer Hashing for Image Retrieval [article]

Shiv Ram Dubey, Satish Kumar Singh, Wei-Ta Chu
2022 arXiv   pre-print
The proposed VTS model is fine tuned for hashing under six different image retrieval frameworks, including Deep Supervised Hashing (DSH), HashNet, GreedyHash, Improved Deep Hashing Network (IDHN), Deep  ...  Deep learning has shown a tremendous growth in hashing techniques for image retrieval. Recently, Transformer has emerged as a new architecture by utilizing self-attention without convolution.  ...  In this paper, we test the VTS performance under six state-of-the-art hashing frameworks, namely Deep Supervised Hashing (DSH) [26] , HashNet [2] , GreedyHash [34] , Improved Deep Hashing Network (IDHN  ... 
arXiv:2109.12564v2 fatcat:6dy2zvoasbdlbjoiguyzd2irrm

Deep Asymmetric Pairwise Hashing

Fumin Shen, Xin Gao, Li Liu, Yang Yang, Heng Tao Shen
2017 Proceedings of the 2017 ACM on Multimedia Conference - MM '17  
Inspired by the latest advance in the asymmetric hashing scheme, in this work, we propose a novel Deep Asymmetric Pairwise Hashing approach (DAPH) for supervised hashing. e core idea is that two deep convolutional  ...  Recently, deep neural networks based hashing methods have greatly improved the multimedia retrieval performance by simultaneously learning feature representations and binary hash functions.  ...  Figure 1 : 1 Overview of the proposed DAPH method. e training procedure includes two stages: the pre-training with the deep residual network (top) and the deep asymmetric hash model training (bottom).  ... 
doi:10.1145/3123266.3123345 dblp:conf/mm/ShenGLYS17 fatcat:shtbbjsr4zbehosjjdwzppqvka

BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label [article]

Shengshan Hu, Ziqi Zhou, Yechao Zhang, Leo Yu Zhang, Yifeng Zheng, Yuanyuan HE, Hai Jin
2022 arXiv   pre-print
Nevertheless, backdoor attack, another famous threat to DNNs, has not been studied for deep hashing yet.  ...  Meanwhile, extensive works have demonstrated that deep neural networks (DNNs) are susceptible to adversarial examples, and exploring adversarial attack against deep hashing has attracted many research  ...  Deep Hashing Model.  ... 
arXiv:2207.00278v3 fatcat:imwg3wumprdgjgmj7bcwrxc7ha
« Previous Showing results 1 — 15 out of 6,480 results