4,373 Hits in 2.8 sec

Deep learning of binary hash codes for fast image retrieval

Kevin Lin, Huei-Fang Yang, Jen-Hao Hsiao, Chu-Song Chen
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
Encouraged by the recent advances in convolutional neural networks (CNNs), we propose an effective deep learning framework to generate binary hash codes for fast image retrieval.  ...  Approximate nearest neighbor search is an efficient strategy for large-scale image retrieval.  ...  In contrast, we present a simple but efficient deep learning approach to learn a set of effective hash-like functions, and it achieves more favorable results on the publicly available datasets.  ... 
doi:10.1109/cvprw.2015.7301269 dblp:conf/cvpr/LinYHC15 fatcat:ldzjg37xlvg3tchpjfvvdpdhvm

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

Zhengyang Yu, Song Wu, Zhihao Dou, Erwin M.Bakker
2021 arXiv   pre-print
Due to its effectivity and efficiency, deep hashing approaches are widely used for large-scale visual search.  ...  and precisely guides a feature learning network to preserve multilabel semantic information using an asymmetric learning strategy.  ...  Acknowledgements This work was supported by the National Natural Science Foundation of China (61806168), Fundamental Research Funds for the Central Universities (SWU117059), and Venture & Innovation Support  ... 
arXiv:2012.03820v3 fatcat:fscm4ggdyrct3o6kso53mmriou

An Efficient Indexing for Content Based Image Retrieval Based on Number of Clusters Using Clustering Technique

Monika Jain, S. K. Singh, Kavita Saxena
2017 International Journal of Artificial Intelligence and Applications for Smart Devices  
This paper focuses on a cluster based indexing technique for achieving efficient and effective retrieval performance.  ...  A new cluster based similarity measure conforming to human perception is applied and shown to be effective. An unsupervised learning technique has been used to find number of clusters.  ...  Our proposed index based on HAC and the related similarity measure is shown to provide an efficient and effective retrieval performance.  ... 
doi:10.14257/ijaiasd.2017.5.1.01 fatcat:ooekqrtzmzeb7bculblaa4axuu

A Review On Search Based Face Annotation Using Weakly Labeled Facial Images

Prof.Borude Krishna
2015 Zenodo  
To tackle this problem,we propose an unsupervised label refinement (ULR) technic for ref ining the labels of web facial images using machine learning techniques.  ...  The chall enging part of search based face annotation task is management of most similar facial images and their weak labels.  ...  Clustering-based approximation (CBA) algorithms are also exploited in this work, which lead to improvement of efficiency and scalability of search based system [1] .  ... 
doi:10.5281/zenodo.1475510 fatcat:kazbpcg3mzhmhmpoxkuk2jxli4

Unsupervised Semantic Deep Hashing [article]

Sheng Jin
2018 arXiv   pre-print
In this paper, we propose a novel unsupervised deep hashing method for large-scale image retrieval.  ...  In real-world application, it is a time-consuming and overloaded task for annotating a large number of images.  ...  These methods are more effective and perform more efficiently in image retrieval task. However, most of these deep hashing methods, except Deep-Bit [21] and DBD-MQ [22] , are pure supervised.  ... 
arXiv:1803.06911v1 fatcat:k7ibf3u5tndlrkuh6vlsgdtgpy

Improved Deep Hashing with Scalable Interblock for Tourist Image Retrieval

Jiangfan Feng, Wenzheng Sun, Boxiang Dong
2021 Scientific Programming  
This paper proposes an improved deep hash to learn enhanced hash codes for tourist image retrieval.  ...  However, their performance depends on the supervised labels, but few labeled temporal and discriminative information is available in tourist images.  ...  Acknowledgments e work was supported by the National Natural Science Foundation of China (41971365) and the Chongqing Research Program of Basic Science and Frontier Technology (cstc2019jcyj-msxmX0131).  ... 
doi:10.1155/2021/9937061 fatcat:gorotnkvubdsxojsmjsezp3bbe

Unsupervised Image Style Embeddings for Retrieval and Recognition Tasks

Siddhartha Gairola, Rajvi Shah, P.J. Narayanan
2020 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)  
The learned embeddings outperform other unsupervised representations for style-based image retrieval task on six datasets that capture different meanings of style.  ...  We propose an unsupervised protocol for learning a neural embedding of visual style of images.  ...  The representations learned under this paradigm are effective and efficient for task-specific retrieval but have practical limitations in terms of generalization and scalability, the biggest one being  ... 
doi:10.1109/wacv45572.2020.9093421 dblp:conf/wacv/GairolaSN20 fatcat:hjd5uc3mz5ewrpafpoouhfkvfu

Online Hashing for Scalable Remote Sensing Image Retrieval

Peng Li, Xiaoyu Zhang, Xiaobin Zhu, Peng Ren
2018 Remote Sensing  
Due to the great success of hashing in the field of natural image retrieval, many efforts have been devoted to develop efficient hashing methods for large-scale RS images retrieval tasks recently.  ...  It is extremely fast to perform image retrieval over such binary codes, because the hamming distance between binary codes can be efficiently calculated with XOR operation even in a modern CPU.  ...  As a result, our proposed method is very suitable and efficient for scalable RS image retrieval tasks.  ... 
doi:10.3390/rs10050709 fatcat:2dbb6rhsb5agha4ve5e6t7dmj4

Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks

Huei-Fang Yang, Kevin Lin, Chu-Song Chen
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Moreover, SSDH performs joint learning of image representations, hash codes, and classification in a point-wised manner, and thus is scalable to large-scale datasets.  ...  With this design, SSDH has a nice characteristic that classification and retrieval are unified in a single learning model.  ...  optimization efficient and scalable.  ... 
doi:10.1109/tpami.2017.2666812 pmid:28207384 fatcat:5u3nhd73qndkpllfcxnjb6m5bi

Exploring Auxiliary Context: Discrete Semantic Transfer Hashing for Scalable Image Retrieval [article]

Lei Zhu, Zi Huang, Zhihui Li, Liang Xie, Heng Tao Shen
2019 arXiv   pre-print
Unsupervised hashing can desirably support scalable content-based image retrieval (SCBIR) for its appealing advantages of semantic label independence, memory and search efficiency.  ...  The whole learning process has linear computation complexity and desirable scalability.  ...  This requirement unfortunately limits the retrieval scalability of hashing in practical image retrieval, where high-quality semantic labels are hard and expensive to obtain. C.  ... 
arXiv:1904.11207v1 fatcat:j3myydxqkza5tntcaidmonzneq

Binary Subspace Coding for Query-by-Image Video Retrieval [article]

Ruicong Xu, Yang Yang, Yadan Luo, Fumin Shen, Zi Huang, Heng Tao Shen
2016 arXiv   pre-print
In this paper, we propose an efficient QBIVR framework to enable an effective and efficient video search with image query.  ...  The query-by-image video retrieval (QBIVR) task has been attracting considerable research attention recently.  ...  However, the QBIVR task is challenged by the similarity-preserving measurement of images and videos and an efficient retrieval method for the huge dataset.  ... 
arXiv:1612.01657v1 fatcat:tnvlgce6efgj5occliq4lwoga4

Learning Global and Local Consistent Representations for Unsupervised Image Retrieval via Deep Graph Diffusion Networks [article]

Zhiyong Dou, Haotian Cui, Lin Zhang, Bo Wang
2020 arXiv   pre-print
GRAD-Net learns semantic representations by exploiting both local and global structures of image manifold in an unsupervised fashion.  ...  Diffusion has shown great success in improving accuracy of unsupervised image retrieval systems by utilizing high-order structures of image manifold.  ...  RELATED WORK Diffusion for Unsupervised Image Retrieval Metric learning has been a central task for image retrieval.  ... 
arXiv:2001.01284v2 fatcat:4df6vmsrxzhehgppiu6637baua

Efficient Binary Coding for Subspace-based Query-by-Image Video Retrieval

Ruicong Xu, Yang Yang, Fumin Shen, Ning Xie, Heng Tao Shen
2017 Proceedings of the 2017 ACM on Multimedia Conference - MM '17  
In particular, the subspace-based query-by-image video retrieval (QBIVR), facing high challenges on similarity-preserving measurements and efficient retrieval schemes, urgently needs considerable research  ...  The merit of this distance metric lies in that it helps to preserve the genuine geometric relationship between query images and database videos to the greatest extent.  ...  However, this task is highly challenging due to the difficulties in designing effective distance functions between images and videos and efficient retrieval schemes for big video datasets.  ... 
doi:10.1145/3123266.3123392 dblp:conf/mm/XuYS0S17 fatcat:aisqgzb7bjdhdlv7k6qckaqimy

Deep Learning for Image Search and Retrieval in Large Remote Sensing Archives [article]

Gencer Sumbul, Jian Kang, Begüm Demir
2020 arXiv   pre-print
This chapter presents recent advances in content based image search and retrieval (CBIR) systems in remote sensing (RS) for fast and accurate information discovery from massive data archives.  ...  Then, we focus our attention on the advances in RS CBIR systems for which deep learning (DL) models are at the forefront.  ...  Most of the existing RS CBIR systems based on DNNs attempt to improve image retrieval performance by: 1) learning discriminative image descriptors; and 2) achieving scalable image search and retrieval.  ... 
arXiv:2004.01613v2 fatcat:d4fjt3vzybbbrejxzobaluqsoq

A Survey on Deep Learning-Driven Remote Sensing Image Scene Understanding: Scene Classification, Scene Retrieval and Scene-Guided Object Detection

Yating Gu, Yantian Wang, Yansheng Li
2019 Applied Sciences  
RSISU includes the following sub-tasks: remote sensing image scene classification, remote sensing image scene retrieval, and scene-driven remote sensing image object detection.  ...  ., speech recognition and natural image recognition), deep learning has also become the state-of-the-art technique in RSISU.  ...  Furthermore, the features learned in an unsupervised way may require longer codes to attain satisfactory results of retrieval, which will largely reduce the image retrieval efficiency.  ... 
doi:10.3390/app9102110 fatcat:oj3acgbmwnhzppxvvjbsn5cfzq
« Previous Showing results 1 — 15 out of 4,373 results