Filters








1,220 Hits in 5.7 sec

Semantic Hierarchy Preserving Deep Hashing for Large-scale Image Retrieval [article]

Ming Zhang, Xuefei Zhe, Le Ou-Yang, Shifeng Chen, Hong Yan
2021 arXiv   pre-print
This paper presents an effective method that preserves the classwise similarity of full-level semantic hierarchy for large-scale image retrieval.  ...  Deep hashing models have been proposed as an efficient method for large-scale similarity search.  ...  Recently, deep hashing has been proposed as a promising method for large-scale image retrieval.  ... 
arXiv:1901.11259v3 fatcat:uyyivhqt6vdirdsbyjp52oj4la

Hierarchy Neighborhood Discriminative Hashing for An Unified View of Single-Label and Multi-Label Image retrieval [article]

Lei Ma, Hongliang Li, Qingbo Wu, Fanman Meng, King Ngi Ngan
2019 arXiv   pre-print
Recently, deep supervised hashing methods have become popular for large-scale image retrieval task.  ...  Finally, we propose a hierarchy neighborhood discriminative hashing loss to unify the single-label and multilabel image retrieval problem with a one-stream deep neural network architecture.  ...  Introduction Hashing [5, 10, 11, [14] [15] [16] [17] 22] has been paid attention by lots of researchers for large-scale image retrieval in recent years.  ... 
arXiv:1901.03060v2 fatcat:ucaepn7j4rfp5pdtl46awv5tay

Semantics Preserving Hierarchy based Retrieval of Indian heritage monuments [article]

Ronak Gupta, Prerana Mukherjee, Brejesh Lall, Varshul Gupta
2020 arXiv   pre-print
In this paper, we propose a framework that utilizes hierarchy to preserve semantic information while performing image classification or image retrieval.  ...  The semantic information preserved in these embeddings helps to classify unknown monuments at higher level of granularity in hierarchy.  ...  In [28] , authors created a large scale noisy Landmarks dataset for image retrieval tasks and also show improvements on the global deep descriptor based on Siamese architecture.  ... 
arXiv:2008.12832v1 fatcat:5uebiugp65hw5ajhlv6hy634ae

Feature Pyramid Hashing [article]

Yifan Yang, Libing Geng, Hanjiang Lai, Yan Pan, Jian Yin
2019 arXiv   pre-print
In recent years, deep-networks-based hashing has become a leading approach for large-scale image retrieval.  ...  Most deep hashing approaches use the high layer to extract the powerful semantic representations.  ...  In this paper, we focus on deep hashing for fine-grained image retrieval. Much effort has been devoted to deep-networks-based hashing for large-scale image retrieval (e.g., [1, 30] ).  ... 
arXiv:1904.02325v1 fatcat:wjp6syjdufd5pezneepvglifaa

Combating Ambiguity for Hash-code Learning in Medical Instance Retrieval [article]

Jiansheng Fang, Huazhu Fu, Dan Zeng, Xiao Yan, Yuguang Yan, Jiang Liu
2021 arXiv   pre-print
To combat the manifestation ambiguity in medical instance retrieval, we propose a novel deep framework called Y-Net, encoding images into compact hash-codes generated from convolutional features by feature  ...  When encountering a dubious diagnostic case, medical instance retrieval can help radiologists make evidence-based diagnoses by finding images containing instances similar to a query case from a large image  ...  hashing for tumor assessment [11] , deep residual hashing for chest X-ray images [36] , order-sensitive deep hashing method for multi-morbidity medical image retrieval [22] , deep disentangled momentum  ... 
arXiv:2105.08872v1 fatcat:5ga4eudoorchja5xwswm453jje

Hierarchical Hashing for Image Retrieval [chapter]

Cheng Yan, Xiao Bai, Jun Zhou, Yun Liu
2017 Communications in Computer and Information Science  
In this paper, we propose a hierarchical hashing method for image retrieval.  ...  Besides standard evaluation criteria, we also developed hierarchical evaluation criteria for image retrieval and classification tasks.  ...  First, we propose a hierarchical hashing for image retrieval on large-scale datasets by combining both semantic level relationship and feature level relationship into a hashing learning objective.  ... 
doi:10.1007/978-981-10-7302-1_10 fatcat:ciaspull3fhgbgulfevujanchu

Supervised Deep Hashing for Hierarchical Labeled Data [article]

Dan Wang, Heyan Huang, Chi Lu, Bo-Si Feng, Liqiang Nie, Guihua Wen, Xian-Ling Mao
2017 arXiv   pre-print
Recently, hashing methods have been widely used in large-scale image retrieval.  ...  In this paper, we propose a novel deep hashing method, called supervised hierarchical deep hashing (SHDH), to perform hash code learning for hierarchical labeled data.  ...  Unsupervised hashing works by preserving the Euclidean similarity between the attributes of training points, while semi-supervised and supervised hashing try to preserve the semantic similarity constructed  ... 
arXiv:1704.02088v3 fatcat:vj7tj44pjbc5pltjkgszemljym

SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval

Peng Xu, Yongye Huang, Tongtong Yuan, Kaiyue Pang, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales, Zhanyu Ma, Jun Guo
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
We propose a deep hashing framework for sketch retrieval that, for the first time, works on a multi-million scale human sketch dataset.  ...  Instead of following the conventional sketch recognition task, we introduce the novel problem of sketch hashing retrieval which is not only more challenging, but also offers a better testbed for large-scale  ...  Recently, deep hashing learning has shown superiority on better preserving the semantic information when compared with shallow methods [28, 14, 21] .  ... 
doi:10.1109/cvpr.2018.00844 dblp:conf/cvpr/0005HYPSXHM018 fatcat:4ec6rhsmnjf7rckiv6nmpofiem

SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval [article]

Peng Xu, Yongye Huang, Tongtong Yuan, Kaiyue Pang, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales, Zhanyu Ma, Jun Guo
2018 arXiv   pre-print
We propose a deep hashing framework for sketch retrieval that, for the first time, works on a multi-million scale human sketch dataset.  ...  Instead of following the conventional sketch recognition task, we introduce the novel problem of sketch hashing retrieval which is not only more challenging, but also offers a better testbed for large-scale  ...  Recently, deep hashing learning has shown superiority on better preserving the semantic information when compared with shallow methods [28, 14, 21] .  ... 
arXiv:1804.01401v1 fatcat:mjxtnavc7verfgvjhpec4qjqju

Learning to hash with semantic similarity metrics and empirical KL divergence [article]

Heikki Arponen, Tom E. Bishop
2020 arXiv   pre-print
Efficiency of the methods is demonstrated with semantic image retrieval on the CIFAR-100, ImageNet and Conceptual Captions datasets, using similarities inferred from the WordNet label hierarchy or sentence  ...  Learning to hash is an efficient paradigm for exact and approximate nearest neighbor search from massive databases.  ...  Recently [1] explored image retrieval (without hashing) using semantic hierarchies to design an embedding space, in a two-step process.  ... 
arXiv:2005.04917v1 fatcat:kd3xdghvajhmxdp3d2mxiifeya

On Learning Semantic Representations for Million-Scale Free-Hand Sketches [article]

Peng Xu, Yongye Huang, Tongtong Yuan, Tao Xiang, Timothy M. Hospedales, Yi-Zhe Song, Liang Wang
2020 arXiv   pre-print
(ii) We propose a deep embedding model for sketch zero-shot recognition, via collecting a large-scale edge-map dataset and proposing to extract a set of semantic vectors from edge-maps as the semantic  ...  Specifically, we use our dual-branch architecture as a universal representation framework to design two sketch-specific deep models: (i) We propose a deep hashing model for sketch retrieval, where a novel  ...  Deep Hashing Learning Hashing is an important research topic for fast image retrieval.  ... 
arXiv:2007.04101v1 fatcat:cng2cw6r5fg43p5erfisj57tu4

Marginalized Graph Attention Hashing for Zero-Shot Image Retrieval

Meixue Huang, Dayan Wu, Wanqian Zhang, Zhi Xiong, Bo Li, Weiping Wang
2020 British Machine Vision Conference  
Zero-shot image retrieval allows to precisely retrieve candidates relevant to unobserved queries, of which categories have never been seen during training.  ...  To tackle these issues, in this paper, we propose a novel deep zero-shot hashing method, named Marginalized Graph Attention Hashing (MGAH).  ...  ImageNet [6] is a large-scale image dataset organized according to WordNet hierarchy.  ... 
dblp:conf/bmvc/HuangWZXLW20 fatcat:bdl2itwg2zfc3le5un5nqba6t4

Zero-shot Hashing with orthogonal projection for image retrieval

Haofeng Zhang, Yang Long, Ling Shao
2018 Pattern Recognition Letters  
Hashing has been widely used in large-scale image retrieval.  ...  In this paper, we propose a novel hashing method based on orthogonal projection of both image and semantic attribute, which constrains the generated binary codes in orthogonal space should be orthogonal  ...  Hashing is a powerful and well-known large-scale image retrieval technique, which encode the real-valued image into binary codes, such as '0/1' or '-1/+1'.  ... 
doi:10.1016/j.patrec.2018.04.011 fatcat:y3oqzqc7efaubb5gej65jmpnvq

Unsupervised deep hashing with stacked convolutional autoencoders

Sovann En, Bruno Cremilleux, Frederic Jurie
2017 2017 IEEE International Conference on Image Processing (ICIP)  
HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not.  ...  The former approach generally does not scale well, making it not suitable for large scale nearest neighbor search [9] .  ...  The capability of our network to produce semantic preserving codes is validated on the MNIST dataset on an image retrieval and image classification tasks.  ... 
doi:10.1109/icip.2017.8296917 dblp:conf/icip/EnCJ17 fatcat:yioqxsazy5d2ld45t2cskevwwi

SitNet: Discrete Similarity Transfer Network for Zero-shot Hashing

Yuchen Guo, Guiguang Ding, Jungong Han, Yue Gao
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
Hashing has been widely utilized for fast image retrieval recently.  ...  In this paper, we propose a novel zero-shot hashing approach, called Discrete Similarity Transfer Network (SitNet), to preserve the semantic similarity between images from both "seen" concepts and new  ...  ImageNet is a large-scale vision dataset organized according to WordNet hierarchy.  ... 
doi:10.24963/ijcai.2017/245 dblp:conf/ijcai/GuoDHG17 fatcat:jnymy3enzrhwxdeysbjkjb3uzu
« Previous Showing results 1 — 15 out of 1,220 results