Geometry Flow-Based Deep Riemannian Metric Learning

Deep metric learning(DML)has achieved great results on visual understanding tasks by seamlessly integrating conventional metric learning with deep neural networks.Existing deep metric learning methods focus on designing pair-based distance loss to decrease intra-class distance while increasing interclass distance.However,these methods fail to preserve the geometric structure of data in the embedding space,which leads to the spatial structure shift across mini-batches and may slow down the convergence of embedding learning.To alleviate these issues,by assuming that the input data is embedded in a lower-dimensional sub-manifold,we propose a novel deep Riemannian metric learning(DRML)framework that exploits the non-Euclidean geometric structural information.Considering that the curvature information of data measures how much the Riemannian(nonEuclidean)metric deviates from the Euclidean metric,we leverage geometry flow,which is called a geometric evolution equation,to characterize the relation between the Riemannian metric and its curvature.Our DRML not only regularizes the local neighborhoods connection of the embeddings at the hidden layer but also adapts the embeddings to preserve the geometric structure of the data.On several benchmark datasets,the proposed DRML outperforms all existing methods and these results demonstrate its effectiveness.

A Network Traffic Classification Model Based on Metric Learning

Attacks on websites and network servers are among the most critical threats in network security.Network behavior identification is one of the most effective ways to identify malicious network intrusions.Analyzing abnormal network traffic patterns and traffic classification based on labeled network traffic data are among the most effective approaches for network behavior identification.Traditional methods for network traffic classification utilize algorithms such as Naive Bayes,Decision Tree and XGBoost.However,network traffic classification,which is required for network behavior identification,generally suffers from the problem of low accuracy even with the recently proposed deep learning models.To improve network traffic classification accuracy thus improving network intrusion detection rate,this paper proposes a new network traffic classification model,called ArcMargin,which incorporates metric learning into a convolutional neural network(CNN)to make the CNN model more discriminative.ArcMargin maps network traffic samples from the same category more closely while samples from different categories are mapped as far apart as possible.The metric learning regularization feature is called additive angular margin loss,and it is embedded in the object function of traditional CNN models.The proposed ArcMargin model is validated with three datasets and is compared with several other related algorithms.According to a set of classification indicators,the ArcMargin model is proofed to have better performances in both network traffic classification tasks and open-set tasks.Moreover,in open-set tasks,the ArcMargin model can cluster unknown data classes that do not exist in the previous training dataset.

Recognition of Group Activities Using Complex Wavelet Domain Based Cayley-Klein Metric Learning

A group activity recognition algorithm is proposed to improve the recognition accuracy in video surveillance by using complex wavelet domain based Cayley-Klein metric learning.Non-sampled dual-tree complex wavelet packet transform(NS-DTCWPT)is used to decompose the human images in videos into multi-scale and multi-resolution.An improved local binary pattern(ILBP)and an inner-distance shape context(IDSC)combined with bag-of-words model is adopted to extract the decomposed high and low frequency coefficient features.The extracted coefficient features of the training samples are used to optimize Cayley-Klein metric matrix by solving a nonlinear optimization problem.The group activities in videos are recognized by using the method of feature extraction and Cayley-Klein metric learning.Experimental results on behave video set,group activity video set,and self-built video set show that the proposed algorithm has higher recognition accuracy than the existing algorithms.

Metric Learning for Semantic Metric Learning for Semantic⁃Based Clothes Retrieval

Existing clothes retrieval methods mostly adopt binary supervision in metric learning.For each iteration,only the clothes belonging to the same instance are positive samples,and all other clothes are“indistinguishable”negative samples,which causes the following problem.The relevance between the query and candidates is only treated as relevant or irrelevant,which makes the model difficult to learn the continu-ous semantic similarities between clothes.Clothes that do not belong to the same instance are completely considered irrelevant and are uni-formly pushed away from the query by an equal margin in the embedding space,which is not consistent with the ideal retrieval results.Moti-vated by this,we propose a novel method called semantic-based clothes retrieval(SCR).In SCR,we measure the semantic similarities be-tween clothes and design a new adaptive loss based on these similarities.The margin in the proposed adaptive loss can vary with different se-mantic similarities between the anchor and negative samples.In this way,more coherent embedding space can be learned,where candidates with higher semantic similarities are mapped closer to the query than those with lower ones.We use Recall@K and normalized Discounted Cu-mulative Gain(nDCG)as evaluation metrics to conduct experiments on the DeepFashion dataset and have achieved better performance.

Vehicle Matching Based on Similarity Metric Learning

With the development of new media technology,vehicle matching plays a further significant role in video surveillance systems.Recent methods explored the vehicle matching based on the feature extraction.Meanwhile,similarity metric learning also has achieved enormous progress in vehicle matching.But most of these methods are less effective in some realistic scenarios where vehicles usually be captured in different times.To address this cross-domain problem,we propose a cross-domain similarity metric learning method that utilizes theGANto generate vehicle imageswith another domain and propose the two-channel Siamese network to learn a similarity metric from both domains(i.e.,Day pattern or Night pattern)for vehicle matching.To exploit properties and relationships among vehicle datasets,we first apply the domain transformer to translate the domain of vehicle images,and then utilize the two-channel Siamese network to extract features from both domains for better feature similarity learning.Experimental results illustrate that our models achieve improvements over state-of-the-arts.

Data-driven Transient Stability Assessment Based on Kernel Regression and Distance Metric Learning

Transient stability assessment(TSA) is of great importance in power systems. For a given contingency, one of the most widely-used transient stability indices is the critical clearing time(CCT), which is a function of the pre-fault power flow.TSA can be regarded as the fitting of this function with the prefault power flow as the input and the CCT as the output. In this paper, a data-driven TSA model is proposed to estimate the CCT. The model is based on Mahalanobis-kernel regression,which employs the Mahalanobis distance in the kernel regression method to formulate a better regressor. A distance metric learning approach is developed to determine the problem-specific distance for TSA, which describes the dissimilarity between two power flow scenarios. The proposed model is more accurate compared to other data-driven methods, and its accuracy can be further improved by supplementing more training samples.Moreover, the model provides the probability density function of the CCT, and different estimations of CCT at different conservativeness levels. Test results verify the validity and the merits of the method.

Face recognition based on subset selection via metric learning on manifold

With the development of face recognition using sparse representation based classification(SRC), many relevant methods have been proposed and investigated. However, when the dictionary is large and the representation is sparse, only a small proportion of the elements contributes to the l1-minimization. Under this observation,several approaches have been developed to carry out an efficient element selection procedure before SRC. In this paper, we employ a metric learning approach which helps find the active elements correctly by taking into account the interclass/intraclass relationship and manifold structure of face images. After the metric has been learned, a neighborhood graph is constructed in the projected space. A fast marching algorithm is used to rapidly select the subset from the graph, and SRC is implemented for classification. Experimental results show that our method achieves promising performance and significant efficiency enhancement.

Discriminative Histogram Intersection Metric Learning and Its Applications

In this paper, a novel method called discriminative histogram intersection metric learning （DHIML） is proposed for pair matching and classification. Specifically, we introduce a discrimination term for learning a metric from binary infor-mation such as same/not-same or similar/dissimilar, and then combine it with the classification error for the discrimination in classifier construction. Compared with conventional approaches, the proposed method has several advantages. 1） The histogram intersection strategy is adopted into metric learning to deal with the widely used histogram features effectively. 2） By introducing discriminative term and classification error term into metric learning, a more discriminative distance metric and a classifier can be learned together. 3） The objective function is robust to outliers and noises for both features and labels in the training. The performance of the proposed method is tested on four applications： face verification, face-track identification, face-track clustering, and image classification. Evaluations on the challenging restricted protocol of Labeled Faces in the Wild （LFW） benchmark, a dataset with more than 7000 face-tracks, and Caltech-101 dataset validate the robustness and discriminability of the proposed metric learning, compared with the recent state-of-the-art approaches.

Online Metric Learning for Relevance Feedback in E-Commerce Image Retrieval Applications

Relevance feedback plays a key role in multiple feature-based image retrieval applications. This paper describes an online metric learning approach for a set of ranking functions. In the feedback round, the most relevant and most nonrelevant images related to the target image are selected to construct a relative comparison triplet. The weighting parameters of the multiple ranking functions are updated by minimizing a quadratic objective function constrained by the triplet. The approach unifies the learning algorithm for the most commonly used ranking functions. Thus, multiple features with their own ranking function can easily be employed in the ranking module without feature reconstruction. The method is computationally inexpensive and appropriate for large-scale e-commerce image retrieval applications. Customized ranking functions are well supported. Practically, simplified ranking functions yield better results when the number of query rounds is relatively small. Experiments with an image dataset from a real e-commerce platform show the superiority of the proposed approach.

Distance metric learning guided adaptive subspace semi-supervised clustering

Most existing semi-supervised clustering algorithms are not designed for handling high- dimensional data. On the other hand, semi-supervised dimensionality reduction methods may not necessarily improve the clustering performance, due to the fact that the inherent relationship between subspace selection and clustering is ignored. In order to mitigate the above problems, we present a semi-supervised clustering algo- rithm using adaptive distance metric learning （SCADM） which performs semi-supervised clustering and distance metric learning simultaneously. SCADM applies the clustering results to learn a distance metric and then projects the data onto a low-dimensional space where the separability of the data is maximized. Experimental results on real-world data sets show that the proposed method can effectively deal with high-dimensional data and provides an appealing clustering performance.

Compositional metric learning for multi-label classification

Multi-label classification aims to assign a set of proper labels for each instance,where distance metric learning can help improve the generalization ability of instance-based multi-label classification models.Existing multi-label metric learning techniques work by utilizing pairwise constraints to enforce that examples with similar label assignments should have close distance in the embedded feature space.In this paper,a novel distance metric learning approach for multi-label classification is proposed by modeling structural interactions between instance space and label space.On one hand,compositional distance metric is employed which adopts the representation of a weighted sum of rank-1 PSD matrices based on com-ponent bases.On the other hand,compositional weights are optimized by exploiting triplet similarity constraints derived from both instance and label spaces.Due to the compositional nature of employed distance metric,the resulting problem admits quadratic programming formulation with linear optimization complexity w.r.t.the number of training examples.We also derive the generalization bound for the proposed approach based on algorithmic robustness analysis of the compositional metric.Extensive experiments on sixteen benchmark data sets clearly validate the usefulness of compositional metric in yielding effective distance metric for multi-label classification.

An effective crack position diagnosis method for the hollow shaft rotor system based on the convolutional neural network and deep metric learning

In recent years, the crack fault is one of the most common faults in the rotor system and it is still a challenge for crack position diagnosis in the hollow shaft rotor system. In this paper, a method based on the Convolutional Neural Network and deep metric learning(CNN-C) is proposed to effectively identify the crack position for a hollow shaft rotor system. Center-loss function is used to enhance the performance of neural network. Main contributions include: Firstly, the dynamic response of the dual-disks hollow shaft rotor system is obtained. The analysis results show that the crack will cause super-harmonic resonance, and the peak value of it is closely related to the position and depth of the crack. In addition, the amplitude near the non-resonant region also has relationship with the crack parameters. Secondly, we proposed an effective crack position diagnosis method which has the highest 99.04% recognition accuracy compared with other algorithms. Then,the influence of penalty factor on CNN-C performance is analyzed, which shows that too high penalty factor will lead to the decline of the neural network performance. Finally, the feature vectors are visualized via t-distributed Stochastic Neighbor Embedding(t-SNE). Naive Bayes classifier(NB) and K-Nearest Neighbor algorithm(KNN) are used to verify the validity of the feature vectors extracted by CNN-C. The results show that NB and KNN have more regular decision boundaries and higher recognition accuracy on the feature vectors data set extracted by CNN-C,indicating that the feature vectors extracted by CNN-C have great intra-class compactness and inter-class separability.

Co-metric： a metric learning algorithm for data with multiple views

We address the problem of metric learning for multi-view data. Many metric learning algorithms have been proposed, most of them focus just on single view circumstances, and only a few deal with multi-view data. In this paper, motivated by the co-training framework, we propose an algorithm-independent framework, named co-metric, to learn Mahalanobis metrics in multi-view settings. In its implementation, an off-the-shelf single-view metric learning algorithm is used to learn metrics in individual views of a few labeled examples. Then the most confidently-labeled examples chosen from the unlabeled set are used to guide the metric learning in the next loop. This procedure is repeated until some stop criteria are met. The framework can accommodate most existing metric learning algorithms whether types-of- side-information or example-labels are used. In addition it can naturally deal with semi-supervised circumstances under more than two views. Our comparative experiments demon- strate its competiveness and effectiveness.

Hybrid Deep Learning-Improved BAT Optimization Algorithm for Soil Classification Using Hyperspectral Features

Now a days,Remote Sensing(RS)techniques are used for earth observation and for detection of soil types with high accuracy and better reliability.This technique provides perspective view of spatial resolution and aids in instantaneous measurement of soil’s minerals and its characteristics.There are a few challenges that is present in soil classification using image enhancement such as,locating and plotting soil boundaries,slopes,hazardous areas,drainage condition,land use,vegetation etc.There are some traditional approaches which involves few drawbacks such as,manual involvement which results in inaccuracy due to human interference,time consuming,inconsistent prediction etc.To overcome these draw backs and to improve the predictive analysis of soil characteristics,we propose a Hybrid Deep Learning improved BAT optimization algorithm(HDIB)for soil classification using remote sensing hyperspectral features.In HDIB,we propose a spontaneous BAT optimization algorithm for feature extraction of both spectral-spatial features by choosing pure pixels from the Hyper Spectral(HS)image.Spectral-spatial vector as training illustrations is attained by merging spatial and spectral vector by means of priority stacking methodology.Then,a recurring Deep Learning(DL)Neural Network(NN)is used for classifying the HS images,considering the datasets of Pavia University,Salinas and Tamil Nadu Hill Scene,which in turn improves the reliability of classification.Finally,the performance of the proposed HDIB based soil classifier is compared and analyzed with existing methodologies like Single Layer Perceptron(SLP),Convolutional Neural Networks(CNN)and Deep Metric Learning(DML)and it shows an improved classification accuracy of 99.87%,98.34%and 99.9%for Tamil Nadu Hills dataset,Pavia University and Salinas scene datasets respectively.

A Local Quadratic Embedding Learning Algorithm and Applications for Soft Sensing

Inspired by the tremendous achievements of meta-learning in various fields,this paper proposes the local quadratic embedding learning(LQEL)algorithm for regression problems based on metric learning and neural networks(NNs).First,Mahalanobis metric learning is improved by optimizing the global consistency of the metrics between instances in the input and output space.Then,we further prove that the improved metric learning problem is equivalent to a convex programming problem by relaxing the constraints.Based on the hypothesis of local quadratic interpolation,the algorithm introduces two lightweight NNs;one is used to learn the coefficient matrix in the local quadratic model,and the other is implemented for weight assignment for the prediction results obtained from different local neighbors.Finally,the two sub-mod els are embedded in a unified regression framework,and the parameters are learned by means of a stochastic gradient descent(SGD)algorithm.The proposed algorithm can make full use of the information implied in target labels to find more reliable reference instances.Moreover,it prevents the model degradation caused by sensor drift and unmeasurable variables by modeling variable differences with the LQEL algorithm.Simulation results on multiple benchmark datasets and two practical industrial applications show that the proposed method outperforms several popular regression methods.

Metric-based Few-shot Classification in Remote Sensing Image

Target recognition based on deep learning relies on a large quantity of samples,but in some specific remote sensing scenes,the samples are very rare.Currently,few-shot learning can obtain high-performance target classification models using only a few samples,but most researches are based on the natural scene.Therefore,this paper proposes a metric-based few-shot classification technology in remote sensing.First,we constructed a dataset(RSD-FSC)for few-shot classification in remote sensing,which contained 21 classes typical target sample slices of remote sensing images.Second,based on metric learning,a k-nearest neighbor classification network is proposed,to find multiple training samples similar to the testing target,and then the similarity between the testing target and multiple similar samples is calculated to classify the testing target.Finally,the 5-way 1-shot,5-way 5-shot and 5-way 10-shot experiments are conducted to improve the generalization of the model on few-shot classification tasks.The experimental results show that for the newly emerged classes few-shot samples,when the number of training samples is 1,5 and 10,the average accuracy of target recognition can reach 59.134%,82.553%and 87.796%,respectively.It demonstrates that our proposed method can resolve few-shot classification in remote sensing image and perform better than other few-shot classification methods.

MEM-TET: Improved Triplet Network for Intrusion Detection System

With the advancement of network communication technology,network traffic shows explosive growth.Consequently,network attacks occur frequently.Network intrusion detection systems are still the primary means of detecting attacks.However,two challenges continue to stymie the development of a viable network intrusion detection system:imbalanced training data and new undiscovered attacks.Therefore,this study proposes a unique deep learning-based intrusion detection method.We use two independent in-memory autoencoders trained on regular network traffic and attacks to capture the dynamic relationship between traffic features in the presence of unbalanced training data.Then the original data is fed into the triplet network by forming a triplet with the data reconstructed from the two encoders to train.Finally,the distance relationship between the triples determines whether the traffic is an attack.In addition,to improve the accuracy of detecting unknown attacks,this research proposes an improved triplet loss function that is used to pull the distances of the same class closer while pushing the distances belonging to different classes farther in the learned feature space.The proposed approach’s effectiveness,stability,and significance are evaluated against advanced models on the Android Adware and General Malware Dataset(AAGM17),Knowledge Discovery and Data Mining Cup 1999(KDDCUP99),Canadian Institute for Cybersecurity Group’s Intrusion Detection Evaluation Dataset(CICIDS2017),UNSW-NB15,Network Security Lab-Knowledge Discovery and Data Mining(NSL-KDD)datasets.The achieved results confirmed the superiority of the proposed method for the task of network intrusion detection.

A Novel Siamese Network for Few/Zero-Shot Handwritten Character Recognition Tasks

Deep metric learning is one of the recommended methods for the challenge of supporting few/zero-shot learning by deep networks.It depends on building a Siamese architecture of two homogeneous Convolutional Neural Networks(CNNs)for learning a distance function that can map input data from the input space to the feature space.Instead of determining the class of each sample,the Siamese architecture deals with the existence of a few training samples by deciding if the samples share the same class identity or not.The traditional structure for the Siamese architecture was built by forming two CNNs from scratch with randomly initialized weights and trained by binary cross-entropy loss.Building two CNNs from scratch is a trial and error and time-consuming phase.In addition,training with binary crossentropy loss sometimes leads to poor margins.In this paper,a novel Siamese network is proposed and applied to few/zero-shot Handwritten Character Recognition(HCR)tasks.The novelties of the proposed network are in.1)Utilizing transfer learning and using the pre-trained AlexNet as a feature extractor in the Siamese architecture.Fine-tuning a pre-trained network is typically faster and easier than building from scratch.2)Training the Siamese architecture with contrastive loss instead of the binary cross-entropy.Contrastive loss helps the network to learn a nonlinear mapping function that enables it to map the extracted features in the vector space with an optimal way.The proposed network is evaluated on the challenging Chars74K datasets by conducting two experiments.One is for testing the proposed network in few-shot learning while the other is for testing it in zero-shot learning.The recognition accuracy of the proposed network reaches to 85.6%and 82%in few-and zero-shot learning respectively.In addition,a comparison between the performance of the proposed Siamese network and the traditional Siamese CNNs is conducted.The comparison results show that the proposed network achieves higher recognition results in less time.The proposed network reduces the training time from days to hours in both experiments.

OSAP‐Loss:Efficient optimization of average precision via involving samples after positive ones towards remote sensing image retrieval

In existing remote sensing image retrieval(RSIR)datasets,the number of images among different classes varies dramatically,which leads to a severe class imbalance problem.Some studies propose to train the model with the ranking‐based metric(e.g.,average precision[AP]),because AP is robust to class imbalance.However,current AP‐based methods overlook an important issue:only optimising samples ranking before each positive sample,which is limited by the definition of AP and is prone to local optimum.To achieve global optimisation of AP,a novel method,namely Optimising Samples after positive ones&AP loss(OSAP‐Loss)is proposed in this study.Specifically,a novel superior ranking function is designed to make the AP loss differentiable while providing a tighter upper bound.Then,a novel loss called Optimising Samples after Positive ones(OSP)loss is proposed to involve all positive and negative samples ranking after each positive one and to provide a more flexible optimisation strategy for each sample.Finally,a graphics processing unit memory‐free mechanism is developed to thoroughly address the non‐decomposability of AP optimisation.Extensive experimental results on RSIR as well as conventional image retrieval datasets show the superiority and competitive performance of OSAP‐Loss compared to the state‐of‐the‐art.

Semi-Supervised Clustering Algorithm Based on Deep Feature Mapping

Clustering analysis is one of the main concerns in data mining.A common approach to the clustering process is to bring together points that are close to each other and separate points that are away from each other.Therefore,measuring the distance between sample points is crucial to the effectiveness of clustering.Filtering features by label information and mea-suring the distance between samples by these features is a common supervised learning method to reconstruct distance metric.However,in many application scenarios,it is very expensive to obtain a large number of labeled samples.In this paper,to solve the clustering problem in the few supervised sample and high data dimensionality scenarios,a novel semi-supervised clustering algorithm is proposed by designing an improved prototype network that attempts to reconstruct the distance metric in the sample space with a small amount of pairwise supervised information,such as Must-Link and Cannot-Link,and then cluster the data in the new metric space.The core idea is to make the similar ones closer and the dissimilar ones further away through embedding mapping.Extensive experiments on both real-world and synthetic datasets show the effectiveness of this algorithm.Average clustering metrics on various datasets improved by 8%compared to the comparison algorithm.