Filters








1,244 Hits in 2.8 sec

Hashing with binary autoencoders

Miguel A. Carreira-Perpinan, Ramin Raziperchikolaei
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We consider the problem of binary hashing, where given a high-dimensional vector x ∈ R D , we want to map it to an L-bit vector z = h(x) ∈ {0, 1} L using a hash function h, while preserving the neighbors  ...  Binary hashing has emerged in recent years as an effective technique for fast search on image (and other) databases.  ...  For hashing, the encoder maps continuous inputs onto binary code vectors with L bits, z ∈ {0, 1} L , and we call it a binary autoencoder (BA).  ... 
doi:10.1109/cvpr.2015.7298654 dblp:conf/cvpr/Carreira-Perpinan15 fatcat:xeup2kio4ngefni3gjrfcs6csm

Hashing with binary autoencoders [article]

Miguel Á. Carreira-Perpiñán, Ramin Raziperchikolaei
2015 arXiv   pre-print
Here, we focus on the binary autoencoder model, which seeks to reconstruct an image from the binary code produced by the hash function.  ...  Image retrieval experiments, using precision/recall and a measure of code utilization, show the resulting hash function outperforms or is competitive with state-of-the-art methods for binary hashing.  ...  We thank Ming-Hsuan Yang and Yi-Hsuan Tsai (UC Merced) for helpful discussions about binary hashing.  ... 
arXiv:1501.00756v1 fatcat:yodertmqgvgrzgisgfp45z23ga

Local Feature Hashing with Binary Autoencoder for Face Recognition

Jing Chen, Yunxiao Zu
2020 IEEE Access  
In this work, we develop an effective learning-based hashing model, namely local feature hashing with binary auto-encoder (LFH-BAE), to directly learn local binary descriptors in the Hamming space.  ...  Specifically, we first introduce a binary auto-encoder to learn a hashing function to project each face region into high-quality binary codes.  ...  feature learning, 2) feature representation based on autoencoders, and 3) binary hashing.  ... 
doi:10.1109/access.2020.2973472 fatcat:ip2ui5lmbbavnn7hetwwsdp4mi

Binary Codes for Tagging X-Ray Images via Deep De-Noising Autoencoders [article]

Antonio Sze-To, Hamid R. Tizhoosh, Andrew K.C. Wong
2016 arXiv   pre-print
In this study, we explored using a deep de-noising autoencoder (DDA), with a new unsupervised training scheme using only backpropagation and dropout, to hash images into binary codes.  ...  The methods which do not need class labels utilize a deep autoencoder for binary hashing, but the code construction involves a specific training algorithm and an ad-hoc regularization technique.  ...  All training images are assigned with both short and long binary codes. A hash table is then used for hashing the training images using the short binary codes as hash keys.  ... 
arXiv:1604.07060v1 fatcat:pd4q4sfmx5cx5o4aw4atykcilq

Unsupervised deep hashing with stacked convolutional autoencoders

Sovann En, Bruno Cremilleux, Frederic Jurie
2017 2017 IEEE International Conference on Image Processing (ICIP)  
Next, we apply the binary relaxation constraints by gradually increasing the α value from 1e −4 until the hash layer contains binary values (with a precision of 1e −3 ).  ...  CONCLUSIONS We proposed a novel architecture based on deep convolutional autoencoders to learn compact binary hash codes.  ... 
doi:10.1109/icip.2017.8296917 dblp:conf/icip/EnCJ17 fatcat:yioqxsazy5d2ld45t2cskevwwi

Deep Hashing for Semi-supervised Content Based Image Retrieval

2018 KSII Transactions on Internet and Information Systems  
Semantically generated binary hash codes can improve content-based image retrieval. These semantic labels / binary hash codes can be generated from unlabeled data using convolutional autoencoders.  ...  Proposed approach uses semi-supervised deep hashing with semantic learning and binary code generation by minimizing the objective function.  ...  In this study we proposed DSH, a combination of convolutional autoencoder with deep hashing to convert an image to binary code by preserving semantic similarity and image structure at the same time.  ... 
doi:10.3837/tiis.2018.08.013 fatcat:lessznvvsva65ip743jbfu425q

Simultaneous Feature Aggregating and Hashing for Large-scale Image Search [article]

Thanh-Toan Do and Dang-Khoa Le Tan and Trung T. Pham and Ngai-Man Cheung
2017 arXiv   pre-print
In addition, we also propose a fast version of the recently-proposed Binary Autoencoder to be used in our proposed framework.  ...  This leads to more discriminative binary hash codes and improved retrieval accuracy.  ...  , Binary Autoencoder (BA) [6] , Spherical Hashing (SPH) [15] , K-means Hashing (KMH) [14] .  ... 
arXiv:1704.00860v1 fatcat:u4kqcacfafbxbhko7tsmm4sdzi

Unsupervised deep hashing for large-scale visual search

Zhaoqiang Xia, Xiaoyi Feng, Jinye Peng, Abdenour Hadid
2016 2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA)  
Within the heterogeneous deep hashing framework, the autoencoder layers with specific constraints are considered to model the nonlinear mapping between features and binary codes.  ...  Learning based hashing plays a pivotal role in large-scale visual search. However, most existing hashing algorithms tend to learn shallow models that do not seek representative binary codes.  ...  The autoencoder layers are used to generate the initial binary codes whereas the RBM layer is utilized to reduce the dimensionality of the binary codes.  ... 
doi:10.1109/ipta.2016.7821007 dblp:conf/ipta/XiaFPH16 fatcat:ye4jtxqphfcgnn7u4foodedxf4

Simultaneous Feature Aggregating and Hashing for Large-Scale Image Search

Thanh-Toan Do, Dang-Khoa Le Tan, Trung T. Pham, Ngai-Man Cheung
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
In addition, we also propose a fast version of the recently-proposed Binary Autoencoder to be used in our proposed framework.  ...  This leads to more discriminative binary hash codes and improved retrieval accuracy.  ...  , Binary Autoencoder (BA) [6] , Spherical Hashing (SPH) [15] , K-means Hashing (KMH) [14] .  ... 
doi:10.1109/cvpr.2017.449 dblp:conf/cvpr/DoTPC17 fatcat:epfuucbpibeuhbo5gog5lmh4d4

A Showcase of the Use of Autoencoders in Feature Learning Applications [chapter]

David Charte, Francisco Charte, María J. del Jesus, Francisco Herrera
2019 Precision Manufacturing  
This work presents these applications and provides details on how autoencoders can perform them, including code samples making use of an R package with an easy-to-use interface for autoencoder design and  ...  Along the way, the explanations on how each learning task has been achieved are provided with the aim to help the reader design their own autoencoders for these or other objectives.  ...  Semantic hashing Semantic hashing [8] is a task consisting on finding short binary codes for data points so that codes with small Hamming distance correspond to similar samples, and those separated by  ... 
doi:10.1007/978-3-030-19651-6_40 dblp:conf/iwinac/CharteCJH19 fatcat:mgl5mbllfje6liprhvhs4fqctq

Learning Deep Binary Descriptor with Multi-quantization

Yueqi Duan, Jiwen Lu, Ziwei Wang, Jianjiang Feng, Jie Zhou
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we propose an unsupervised feature learning method called deep binary descriptor with multiquantization (DBD-MQ) for visual matching.  ...  with a fine-grained multi-quantization.  ...  error of x n with the kth AutoEncoder.  ... 
doi:10.1109/cvpr.2017.516 dblp:conf/cvpr/DuanLWFZ17 fatcat:wzqgayi7drfr5oacakk24abnba

Enhanced Disease Identification Model for Tea Plant Using Deep Learning

Santhana Krishnan Jayapal, Sivakumar Poruran
2023 Intelligent Automation and Soft Computing  
Deep Hashing with Integrated Autoencoders is our proposed method for image retrieval in Tea Leaf images. It is an efficient and flexible way of retrieving Tea Leaf images.  ...  The autoencoders used with skip connections increase the weightage of the prominent features present in the previous tensor.  ...  Acknowledgement: The authors would like to thank United Planters' Association of Southern India (UPASI) for providing us with the necessary help in obtaining the images for the dataset from the Tea Estate  ... 
doi:10.32604/iasc.2023.026564 fatcat:umrnsvjkpbai7kzi4752upwnhe

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

Shiv Ram Dubey
2020 arXiv   pre-print
have utilized a relaxed binary autoencoder (RBA) to learn the image description for retrieval along with feature aggregation [153] .  ...  In 2015, the binary autoencoder model is used to learn the binary code for fast image retrieval by reconstructing the image from that binary code function [152] .  ... 
arXiv:2012.00641v1 fatcat:2zcho2szpzcc3cs6uou3jpcley

Learning Similarity Preserving Binary Codes for Recommender Systems [article]

Yang Shi, Young-joo Chung
2022 arXiv   pre-print
Hashing-based Recommender Systems (RSs) are widely studied to provide scalable services.  ...  The result demonstrated that although differentiable scaled tanh is popular in recent discrete feature learning literature, a huge performance drop occurs when outputs of scaled tanh are forced to be binary  ...  All features are rounded to the closest binary code with median threshold. (5) AECF We use autoencoders introduced in Section 4 with a rating reconstruction loss.  ... 
arXiv:2204.08569v1 fatcat:ozzka7hm7rbibgne7hmqhhceqe

Simultaneous Feature Aggregating and Hashing for Compact Binary Code Learning [article]

Thanh-Toan Do, Khoa Le, Tuan Hoang, Huu Le, Tam V. Nguyen, Ngai-Man Cheung
2019 arXiv   pre-print
Furthermore, we also propose a fast version of the state-of-the-art hashing method Binary Autoencoder to be used in our proposed frameworks.  ...  This global vector is then subjected to a hashing function to generate a binary hash code. In previous works, the aggregating and the hashing processes are designed independently.  ...  Hence, we solve this optimization with the proposed Relaxed Binary Autoencoder (Section III).  ... 
arXiv:1904.11820v1 fatcat:22dl2zp2zfeito6lqx3x4uyaoa
« Previous Showing results 1 — 15 out of 1,244 results