scholarly journals Unsupervised Hashing with Gradient Attention

Symmetry ◽  
2020 ◽  
Vol 12 (7) ◽  
pp. 1193
Author(s):  
Shaochen Jiang ◽  
Liejun Wang ◽  
Shuli Cheng ◽  
Anyu Du ◽  
Yongming Li
Keyword(s):  
Gradient Descent ◽  
Network Models ◽  
Image Features ◽  
Similarity Matrix ◽  
Hash Code ◽  
Unsupervised Training ◽  
Public Datasets ◽  
Cosine Distance ◽  
Hash Codes ◽  
Trained Network

The existing learning-based unsupervised hashing method usually uses a pre-trained network to extract features, and then uses the extracted feature vectors to construct a similarity matrix which guides the generation of hash codes through gradient descent. Existing research shows that the algorithm based on gradient descent will cause the hash codes of the paired images to be updated toward each other’s position during the training process. For unsupervised training, this situation will cause large fluctuations in the hash code during training and limit the learning efficiency of the hash code. In this paper, we propose a method named Deep Unsupervised Hashing with Gradient Attention (UHGA) to solve this problem. UHGA mainly includes the following contents: (1) use pre-trained network models to extract image features; (2) calculate the cosine distance of the corresponding features of the pair of images, and construct a similarity matrix through the cosine distance to guide the generation of hash codes; (3) a gradient attention mechanism is added during the training of the hash code to pay attention to the gradient. Experiments on two existing public datasets show that our proposed method can obtain more discriminating hash codes.

scholarly journals MLS3RDUH: Deep Unsupervised Hashing via Manifold based Local Semantic Similarity Structure Reconstructing

2020 ◽  
Author(s):  
Rong-Cheng Tu ◽  
Xian-Ling Mao ◽  
Wei Wei
Keyword(s):  
Semantic Similarity ◽  
State Of The Art ◽  
Feature Space ◽  
Similarity Matrix ◽  
Retrieval Performance ◽  
Nearest Neighbours ◽  
Similarity Structure ◽  
Similarity Preserving ◽  
Public Datasets ◽  
Hash Codes

Most of the unsupervised hashing methods usually map images into semantic similarity-preserving hash codes by constructing local semantic similarity structure as guiding information, i.e., treating each point similar to its k nearest neighbours. However, for an image, some of its k nearest neighbours may be dissimilar to it, i.e., they are noisy datapoints which will damage the retrieval performance. Thus, to tackle this problem, in this paper, we propose a novel deep unsupervised hashing method, called MLS3RDUH, which can reduce the noisy datapoints to further enhance retrieval performance. Specifically, the proposed method first defines a novel similarity matrix by utilising the intrinsic manifold structure in feature space and the cosine similarity of datapoints to reconstruct the local semantic similarity structure. Then a novel log-cosh hashing loss function is used to optimize the hashing network to generate compact hash codes by incorporating the defined similarity as guiding information. Extensive experiments on three public datasets show that the proposed method outperforms the state-of-the-art baselines.

scholarly journals Non-Intrusive Load Monitoring Based on Deep Pairwise-Supervised Hashing to Detect Unidentified Appliances

Processes ◽  
2021 ◽  
Vol 9 (3) ◽  
pp. 505
Author(s):  
Qiang Zhao ◽  
Yao Xu ◽  
Zhenfan Wei ◽  
Yinghua Han
Keyword(s):  
Data Stream ◽  
Deep Neural Networks ◽  
Feature Learning ◽  
Identification Accuracy ◽  
Power System Monitoring ◽  
Hash Code ◽  
Load Monitoring ◽  
New Codes ◽  
Public Datasets ◽  
Hash Codes

Non-intrusive load monitoring (NILM) is a fast developing technique for appliances operation recognition in power system monitoring. At present, most NILM algorithms rely on the assumption that all fluctuations in the data stream are triggered by identified appliances. Therefore, NILM of identifying unidentified appliances is still an open challenge. To pursue a scalable solution to energy monitoring for contemporary unidentified appliances, we propose a voltage-current (V-I) trajectory enabled deep pairwise-supervised hashing (DPSH) method for NILM. DPSH performs simultaneous feature learning and hash-code learning with deep neural networks, which shows higher identification accuracy than a benchmark method. DPSH can generate different hash codes to distinguish identified appliances. For unidentified appliances, it generates completely new codes that are different from codes of multiple identified appliances to distinguish them. Experiments on public datasets show that our method can get better F1-score than the benchmark method to achieve state-of-the-art performance in the identification of unidentified appliances, and this method maintains high sustainability to identify other unidentified appliances through retraining. DPSH can be resilient against appliance changes in the house.

scholarly journals A Multi-view Fusion Method via Tensor Learning and Gradient Descent for Image Features

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
LaiHang Yu ◽  
DongYan Zhang ◽  
NingZhong Liu ◽  
WenGang Zhou
Keyword(s):  
Gradient Descent ◽  
Image Features ◽  
Fusion Method

scholarly journals Exploring Optimized Spiking Neural Network Architectures for Classification Tasks on Embedded Platforms

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3240
Author(s):  
Tehreem Syed ◽  
Vijay Kakani ◽  
Xuenan Cui ◽  
Hakil Kim
Keyword(s):  
Neural Networks ◽  
Gradient Descent ◽  
Spiking Neural Networks ◽  
License Plate ◽  
Training Techniques ◽  
Neuromorphic Hardware ◽  
Private And Public ◽  
Embedded Platforms ◽  
Public Datasets ◽  
Event Based

In recent times, the usage of modern neuromorphic hardware for brain-inspired SNNs has grown exponentially. In the context of sparse input data, they are undertaking low power consumption for event-based neuromorphic hardware, specifically in the deeper layers. However, using deep ANNs for training spiking models is still considered as a tedious task. Until recently, various ANN to SNN conversion methods in the literature have been proposed to train deep SNN models. Nevertheless, these methods require hundreds to thousands of time-steps for training and still cannot attain good SNN performance. This work proposes a customized model (VGG, ResNet) architecture to train deep convolutional spiking neural networks. In this current study, the training is carried out using deep convolutional spiking neural networks with surrogate gradient descent backpropagation in a customized layer architecture similar to deep artificial neural networks. Moreover, this work also proposes fewer time-steps for training SNNs with surrogate gradient descent. During the training with surrogate gradient descent backpropagation, overfitting problems have been encountered. To overcome these problems, this work refines the SNN based dropout technique with surrogate gradient descent. The proposed customized SNN models achieve good classification results on both private and public datasets. In this work, several experiments have been carried out on an embedded platform (NVIDIA JETSON TX2 board), where the deployment of customized SNN models has been extensively conducted. Performance validations have been carried out in terms of processing time and inference accuracy between PC and embedded platforms, showing that the proposed customized models and training techniques are feasible for achieving a better performance on various datasets such as CIFAR-10, MNIST, SVHN, and private KITTI and Korean License plate dataset.

scholarly journals A Mobile-Oriented System for Integrity Preserving in Audio Forensics

2019 ◽  
Vol 9 (15) ◽  
pp. 3097 ◽  
Author(s):  
Diego Renza ◽  
Jaime Andres Arango ◽  
Dora Maria Ballesteros
Keyword(s):  
Computational Cost ◽  
Digital Evidence ◽  
Audio Signals ◽  
Audio Forensics ◽  
Audio Recordings ◽  
Hash Code ◽  
Chain Of Custody ◽  
Code Changes ◽  
Hash Codes

This paper addresses a problem in the field of audio forensics. With the aim of providing a solution that helps Chain of Custody (CoC) processes, we propose an integrity verification system that includes capture (mobile based), hash code calculation and cloud storage. When the audio is recorded, a hash code is generated in situ by the capture module (an application), and it is sent immediately to the cloud. Later, the integrity of the audio recording given as evidence can be verified according to the information stored in the cloud. To validate the properties of the proposed scheme, we conducted several tests to evaluate if two different inputs could generate the same hash code (collision resistance), and to evaluate how much the hash code changes when small changes occur in the input (sensitivity analysis). According to the results, all selected audio signals provide different hash codes, and these values are very sensitive to small changes over the recorded audio. On the other hand, in terms of computational cost, less than 2 s per minute of recording are required to calculate the hash code. With the above results, our system is useful to verify the integrity of audio recordings that may be relied on as digital evidence.

scholarly journals AVBH: Asymmetric Learning to Hash with Variable Bit Encoding

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Yanduo Ren ◽  
Jiangbo Qian ◽  
Yihong Dong ◽  
Yu Xin ◽  
Huahui Chen
Keyword(s):  
Low Frequency ◽  
Large Data ◽  
Data Retrieval ◽  
Query Point ◽  
Compact Binary ◽  
Hash Code ◽  
Asymmetric Learning ◽  
Learning To Hash ◽  
Public Datasets ◽  
The Cost

Nearest neighbour search (NNS) is the core of large data retrieval. Learning to hash is an effective way to solve the problems by representing high-dimensional data into a compact binary code. However, existing learning to hash methods needs long bit encoding to ensure the accuracy of query, and long bit encoding brings large cost of storage, which severely restricts the long bit encoding in the application of big data. An asymmetric learning to hash with variable bit encoding algorithm (AVBH) is proposed to solve the problem. The AVBH hash algorithm uses two types of hash mapping functions to encode the dataset and the query set into different length bits. For datasets, the hash code frequencies of datasets after random Fourier feature encoding are statistically analysed. The hash code with high frequency is compressed into a longer coding representation, and the hash code with low frequency is compressed into a shorter coding representation. The query point is quantized to a long bit hash code and compared with the same length cascade concatenated data point. Experiments on public datasets show that the proposed algorithm effectively reduces the cost of storage and improves the accuracy of query.

scholarly journals Research of collision properties of the modified UMAC algorithm on crypto-code constructions

2022 ◽  
pp. 34-43
Author(s):  
Serhii Yevseiev ◽  
Alla Havrylova ◽  
Olha Korol ◽  
Oleh Dmitriiev ◽  
Oleksii Nesmiian ◽  
...  
Keyword(s):  
Authentication Codes ◽  
Advantages And Disadvantages ◽  
Universal Hashing ◽  
Practical Research ◽  
Hash Code ◽  
Last Stage ◽  
Code Constructions ◽  
Transfer Of Information ◽  
The Impact ◽  
Hash Codes

The transfer of information by telecommunication channels is accompanied by message hashing to control the integrity of the data and confirm the authenticity of the data. When using a reliable hash function, it is computationally difficult to create a fake message with a pre-existing hash code, however, due to the weaknesses of specific hashing algorithms, this threat can be feasible. To increase the level of cryptographic strength of transmitted messages over telecommunication channels, there are ways to create hash codes, which, according to practical research, are imperfect in terms of the speed of their formation and the degree of cryptographic strength. The collisional properties of hashing functions formed using the modified UMAC algorithm using the methodology for assessing the universality and strict universality of hash codes are investigated. Based on the results of the research, an assessment of the impact of the proposed modifications at the last stage of the generation of authentication codes on the provision of universal hashing properties was presented. The analysis of the advantages and disadvantages that accompany the formation of the hash code by the previously known methods is carried out. The scheme of cascading generation of data integrity and authenticity control codes using the UMAC algorithm on crypto-code constructions has been improved. Schemes of algorithms for checking hash codes were developed to meet the requirements of universality and strict universality. The calculation and analysis of collision search in the set of generated hash codes was carried out according to the requirements of a universal and strictly universal class for creating hash codes

scholarly journals A Multibranch of Convolutional Neural Network Models for Electroencephalogram-Based Motor Imagery Classification

Biosensors ◽  
2022 ◽  
Vol 12 (1) ◽  
pp. 22
Author(s):  
Ghadir Ali Altuwaijri ◽  
Ghulam Muhammad
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Motor Imagery ◽  
Classification Accuracy ◽  
Network Models ◽  
Classification Methods ◽  
Neural Network Models ◽  
High Gamma ◽  
Public Datasets ◽  
High Level

Automatic high-level feature extraction has become a possibility with the advancement of deep learning, and it has been used to optimize efficiency. Recently, classification methods for convolutional neural network (CNN)-based electroencephalography (EEG) motor imagery have been proposed, and have achieved reasonably high classification accuracy. These approaches, however, use the CNN single convolution scale, whereas the best convolution scale varies from subject to subject. This limits the precision of classification. This paper proposes multibranch CNN models to address this issue by effectively extracting the spatial and temporal features from raw EEG data, where the branches correspond to different filter kernel sizes. The proposed method’s promising performance is demonstrated by experimental results on two public datasets, the BCI Competition IV 2a dataset and the High Gamma Dataset (HGD). The results of the technique show a 9.61% improvement in the classification accuracy of multibranch EEGNet (MBEEGNet) from the fixed one-branch EEGNet model, and 2.95% from the variable EEGNet model. In addition, the multibranch ShallowConvNet (MBShallowConvNet) improved the accuracy of a single-scale network by 6.84%. The proposed models outperformed other state-of-the-art EEG motor imagery classification methods.

scholarly journals Unsupervised Controllable Text Formalization

2019 ◽  
Vol 33 ◽  
pp. 6554-6561
Author(s):  
Parag Jain ◽  
Abhijit Mishra ◽  
Amar Prakash Azad ◽  
Karthik Sankaranarayanan
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Parallel Corpus ◽  
Training Scheme ◽  
Input Text ◽  
Learning Scheme ◽  
Input Control ◽  
Unsupervised Training ◽  
Run Time ◽  
Public Datasets

We propose a novel framework for controllable natural language transformation. Realizing that the requirement of parallel corpus is practically unsustainable for controllable generation tasks, an unsupervised training scheme is introduced. The crux of the framework is a deep neural encoder-decoder that is reinforced with text-transformation knowledge through auxiliary modules (called scorers). These scorers, based on off-the-shelf language processing tools, decide the learning scheme of the encoder-decoder based on its actions. We apply this framework for the text-transformation task of formalizing an input text by improving its readability grade; the degree of required formalization can be controlled by the user at run-time. Experiments on public datasets demonstrate the efficacy of our model towards: (a) transforming a given text to a more formal style, and (b) varying the amount of formalness in the output text based on the specified input control. Our code and datasets are released for academic use.

Sign in / Sign up

Export Citation Format

Share Document