5,010 Hits in 5.9 sec

Learning Robust Hash Codes for Multiple Instance Image Retrieval [article]

Sailesh Conjeti, Magdalini Paschali, Amin Katouzian, Nassir Navab
2017 arXiv   pre-print
In this paper, for the first time, we introduce a multiple instance (MI) deep hashing technique for learning discriminative hash codes with weak bag-level supervision suited for large-scale retrieval.  ...  For better trainability and retrieval quality, we propose a two-pronged approach that includes robust optimization and training with an auxiliary single instance hashing arm which is down-regulated gradually  ...  Conclusion In this paper, for the first time, we proposed an end-to-end deep robust hashing framework, termed RMIH, for retrieval under a multiple instance setting.  ... 
arXiv:1703.05724v1 fatcat:kzak3jraubd33lpsosuteomdpi

Region-DH: Region-based Deep Hashing for Multi-Instance Aware Image Retrieval

Franck Romuald Fotso Mtope, Bo Wei
2020 2020 International Joint Conference on Neural Networks (IJCNN)  
This paper introduces an instance-aware hashing approach Region-DH for large-scale multi-label image retrieval.  ...  We design a unified deep neural network that simultaneously localizes and recognizes objects while learning the hash functions for binary codes.  ...  The instance similarity is simultaneously used for feature learning and hash coding.  ... 
doi:10.1109/ijcnn48605.2020.9207485 dblp:conf/ijcnn/MtopeW20 fatcat:zvyrgns65vfabgyui6sy2rxiwa

Self-supervised asymmetric deep hashing with margin-scalable constraint [article]

Zhengyang Yu, Song Wu, Zhihao Dou, Erwin M.Bakker
2021 arXiv   pre-print
However, it is still challenging to produce compact and discriminative hash codes for images associated with multiple semantics for two main reasons, 1) similarity constraints designed in most of the existing  ...  By further exploiting semantic dictionaries, a new margin-scalable constraint is employed for both precise similarity searching and robust hash code generation.  ...  Program for Chongqing Overseas Returnees (CX2018075).  ... 
arXiv:2012.03820v3 fatcat:fscm4ggdyrct3o6kso53mmriou

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

Shiv Ram Dubey
2020 arXiv   pre-print
This paper presents a comprehensive survey of deep learning based developments in the past decade for content based image retrieval.  ...  Generally, the similarity between the representative features of the query image and dataset images is used to rank the images for retrieval.  ...  In 2020, Chen et al. have proposed a deep multiple-instance ranking based hashing (DMIRH) model for multi-label image retrieval by employing the category-aware bag of feature [212] .  ... 
arXiv:2012.00641v1 fatcat:2zcho2szpzcc3cs6uou3jpcley

Efficient Visual Recognition

Li Liu, Matti Pietikäinen, Jie Qin, Wanli Ouyang, Luc Van Gool
2020 International Journal of Computer Vision  
binary codes for personal- ized image retrieval Personalized image retrieval A general framework for deep supervised discrete hashing Image retrieval Product quantization network for fast visual  ...  search Image and video retrieval Weakly-supervised semantic guided hashing for social image retrieval Social image retrieval Anchor-based self-ensembling for semisupervised deep pairwise hashing  ... 
doi:10.1007/s11263-020-01351-w fatcat:mbcq6shmerbo5njayscgb3t4rq

Hierarchical semantic interaction-based deep hashing network for cross-modal retrieval

Shubai Chen, Song Wu, Li Wang
2021 PeerJ Computer Science  
for high-performance cross-modal hashing retrieval.  ...  Due to the high efficiency of hashing technology and the high abstraction of deep networks, deep hashing has achieved appealing effectiveness and efficiency for large-scale cross-modal retrieval.  ...  Dual-similarity measurement For most cross-modal retrieval benchmark datasets, it is common for an image or text to have multiple labels.  ... 
doi:10.7717/peerj-cs.552 pmid:34141884 pmcid:PMC8176532 fatcat:7m3vtgxggzgwxemjr25nxgqnxy

Discriminative Supervised Hashing for Cross-Modal similarity Search [article]

Jun Yu, Xiao-Jun Wu, Josef Kittler
2019 arXiv   pre-print
Hashing (DSH), to learn the discrimative unified binary codes for multi-modal data.  ...  As multiple modal data reflect similar semantic content, many researches aim at learning unified binary codes. However, discriminative hashing features learned by these methods are not adequate.  ...  Generating Hash Codes For an unseen sample, we can generate a binary code by the learned hash function.  ... 
arXiv:1812.07660v3 fatcat:mijrrvmasngujk4hd2j67upuby

Hashing with Binary Matrix Pursuit [chapter]

Fatih Cakir, Kun He, Stan Sclaroff
2018 Lecture Notes in Computer Science  
and more robust codes.  ...  Incorporating our findings, we propose a novel two-stage hashing method that significantly outperforms previous hashing studies on widely used image retrieval benchmarks.  ...  The authors thank Sarah Adel Bargal for helpful discussions. This work is primarily conducted at Boston University, supported in part by a BU IGNITION award, and equipment donated by NVIDIA.  ... 
doi:10.1007/978-3-030-01228-1_21 fatcat:mhaeamzhaneq3lywkpgl5dawvq

Anchor Graph Structure Fusion Hashing for Cross-Modal Similarity Search [article]

Lu Wang, Jie Yang, Masoumeh Zareapoor, Zhonglong Zheng
2022 arXiv   pre-print
Furthermore, a discrete optimization framework is designed to learn the unified binary codes. Extensive experimental results on three public social datasets demonstrate the superiority of AGSFH.  ...  existing CMH methods relax the discrete constraints to solve the optimization objective, significantly degrading the retrieval performance.  ...  Cross View Hashing (CVH) extends the single-modal spectral hashing to multiple modalities and relaxes the minimization problem for learning the hash codes [21] .  ... 
arXiv:2202.04327v1 fatcat:oxdytmhxyzavnetqbobl4dueka

Hashing with Binary Matrix Pursuit [article]

Fatih Cakir, Kun He, Stan Sclaroff
2018 arXiv   pre-print
and more robust codes.  ...  Incorporating our findings, we propose a novel two-stage hashing method that significantly outperforms previous hashing studies on widely used image retrieval benchmarks.  ...  The authors thank Sarah Adel Bargal for helpful discussions. This work is primarily conducted at Boston University, supported in part by a BU IGNITION award, and equipment donated by NVIDIA.  ... 
arXiv:1808.01990v1 fatcat:lpembrsfqjhf7kci5sihy23usu

Unsupervised Deep Hashing With Pseudo Labels for Scalable Image Retrieval

Haofeng Zhang, Li Liu, Yang Long, Ling Shao
2018 IEEE Transactions on Image Processing  
In order to achieve efficient similarity searching, hash functions are designed to encode images into lowdimensional binary codes with the constraint that similar features will have a short distance in  ...  However, without label information, most state-of-the-art unsupervised deep hashing (DH) algorithms suffer from severe performance degradation for unsupervised scenarios.  ...  By incorporating these criteria into our unified framework, the resultant hash code is more robust for largescale retrieval tasks on different benchmarks.  ... 
doi:10.1109/tip.2017.2781422 pmid:29324416 fatcat:ks6cfierdvcrreq5w644pql3ou

Supervised Short-Length Hashing

Xingbo Liu, Xiushan Nie, Quan Zhou, Xiaoming Xi, Lei Zhu, Yilong Yin
2019 Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence  
However, when retrieving using an extremely short length hash code learned by the existing methods, the performance cannot be guaranteed because of severe information loss.  ...  To the best of our knowledge, this is the first linear-based hashing method that focuses on both short and long-length hash codes for maintaining high precision.  ...  Natural Science Foundation of China (61876098, 61671274, 61573219), China Postdoctoral Science Foundation (2016M592190), Shandong Provincial Key Research and Development Plan (2017CXGC1504), Special funds for  ... 
doi:10.24963/ijcai.2019/420 dblp:conf/ijcai/LiuNZX0Y19 fatcat:23nemx2zabcwzgcydin3ugxqay

Deep Multi-View Enhancement Hashing for Image Retrieval [article]

Chenggang Yan, Biao Gong, Yuxuan Wei, Yue Gao
2020 arXiv   pre-print
This is a completely new hash learning method that combines multi-view and deep learning methods.  ...  However, large-scale high-speed retrieval through binary code has a certain degree of reduction in retrieval accuracy compared to traditional retrieval methods.  ...  In this work, a supervised multi-view hashing method called D-MVE-Hash is proposed for accurate and efficient image retrieval based on multiple visual features, multiview hash and deep learning.  ... 
arXiv:2002.00169v2 fatcat:rdmr3p6fqjct3joywouap3dgmu

Improved Deep Hashing with Soft Pairwise Similarity for Multi-label Image Retrieval [article]

Zheng Zhang, Qin Zou, Yuewei Lin, Long Chen, Song Wang
2019 arXiv   pre-print
Hash coding has been widely used in the approximate nearest neighbor search for large-scale image retrieval.  ...  In this paper, a new deep hashing method is proposed for multi-label image retrieval by re-defining the pairwise similarity into an instance similarity, where the instance similarity is quantified into  ...  [43] proposes an online multiple kernel learning method, which aims to find the optimal combination of multiple kernels for similarity learning, and [44] improves the online multi-kernel learning  ... 
arXiv:1803.02987v3 fatcat:koevkgmdtjgxpomsqwcaygi2zy

Latent semantic sparse hashing for cross-modal similarity search

Jile Zhou, Guiguang Ding, Yuchen Guo
2014 Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval - SIGIR '14  
Similarity search methods based on hashing for effective and efficient cross-modal retrieval on large-scale multimedia databases with massive text and images have attracted considerable attention.  ...  In particular, LSSH uses Sparse Coding to capture the salient structures of images, and Matrix Factorization to learn the latent concepts from text.  ...  Up) Existing CMH methods learn independent hash codes for each modal of instances.  ... 
doi:10.1145/2600428.2609610 dblp:conf/sigir/ZhouDG14 fatcat:7mkvr5ijyvfxlcc2aryrhtefzm
« Previous Showing results 1 — 15 out of 5,010 results