Invariant Feature Representation Research Articles

Multiple Adverse Weather Conditions Adaptation for Object Detection via Causal Intervention.

Most state-of-the-art object detection methods have achieved impressive perfomrace on several public benchmarks, which are trained with high definition images. However, existing detectors are often sensitive to the visual variations and out-of-distribution data due to the domain gap caused by various confounders, e.g. the adverse weathre conditions. To bridge the gap, previous methods have been mainly exploring domain alignment, which requires to collect an amount of domain-specific training samples. In this paper, we introduce a novel domain adaptation model to discover a weather condition invariant feature representation. Specifically, we first employ a memory network to develop a confounder dictionary, which stores prototypes of object features under various scenarios. To guarantee the representativeness of each prototype in the dictionary, a dynamic item extraction strategy is used to update the memory dictionary. After that, we introduce a causal intervention reasoning module to explore the invariant representation of a specific object under different weather conditions. Finally, a categorical consistency regularization is used to constrain the similarities between categories in order to automatically search for the aligned instances among distinct domains. Experiments are conducted on several public benchmarks (RTTS, Foggy-Cityscapes, RID, and BDD 100K) with state-of-the-art performance achieved under multiple weather conditions.

Multi-domain Adversarial Variational Bayesian Inference for Domain Generalization

Domain generalization aims to learn common knowledge from multiple observed source domains and transfer it to unseen target domains, e.g. the object recognition in varieties of visual environments. Traditional domain generalization methods aim to learn the feature representation of the raw data with its distribution invariant across domains. This relies on the assumption that the two posterior distributions (the distributions of the label given the feature distribution and given the raw data) are stable in different domains. However, this does not always hold in many practical situations. In this paper, we relax the above assumption by permitting the posterior distribution of the label given the raw data changes in difference domains, and thus focuses on a more realistic learning problem that infers the conditional domain-invariant feature representation. Specifically, a multi-domain adversarial variational Bayesian inference approach is proposed to minimize the inter-domain discrepancy of the conditional distributions of the feature given the label. Besides, it is imposed by the constraints from the adversarial learning and feedback mechanism to enhance the condition invariant feature representation. The extensive experiments on two datasets demonstrate the effectiveness of our approach, as well as the state-of-the-art performance comparing with thirteen methods.

Invariant Feature Encoding for Contact Handprints Using Delaunay Triangulated Graph

Contact-based biometric applications primarily use prints from a finger or a palm for a single instance in different applications. For access control, there is an enrollment process using one or more templates which are compared with verification images. In forensics applications, randomly located, partial, and often degraded prints acquired from a crime scene are compared with the images captured from suspects or existing fingerprint databases, like AFIS. In both scenarios, if we need to use handprints which include segments from the finger and palm, what would be the solution? The motivation behind this is the concept of one single algorithm for one hand. Using an algorithm that can incorporate both prints in a common processing framework can be an alternative which will have advantages like scaling to larger existing databases. This work proposes a method that uses minutiae or minutiae-like features, Delaunay triangulation and graph matching with invariant feature representation to overcome the effects of rotation and scaling. Since palm prints have a large surface area with degradation, they tend to have many false minutiae compared to fingerprints, and the existing palm print algorithms fail to tackle this. The proposed algorithm constructs Delaunay triangulated graphs (DTG) using minutiae where Delaunay triangles form from minutiae, and initiate a collection of base triangles for opening the matching process. Several matches may be observed for a single triangle match when two images are compared. Therefore, the set of initially matched triangles may not be a true set of matched triangles. Each matched triangle is then used to extend as a sub-graph, adding more nodes to it until a maximum graph size is reached. When a significant region of the template image is matched with the test image, the highest possible order of this graph will be obtained. To prove the robustness of the algorithm to geometrical variations and working ability with extremely degraded (similar to latent prints) conditions, it is demonstrated with a subset of partial-quality and extremely-low-quality images from the FVC (fingerprint) and the THUPALMLAB (palm print) databases with and without geometrical variations. The algorithm is useful when partial matches between template and test are expected, and alignment or geometrical normalization is not accurately possible in pre-processing. It will also work for cross-comparisons between images that are not known a priori.

BDNet: A BERT-based dual-path network for text-to-image cross-modal person re-identification

Text-to-image person re-identification (TI-ReID) aims to provide a descriptive sentence to find a specific person in the gallery. The task is very challenging due to the huge feature differences between both image and text descriptions. Currently, most approaches use the idea of combining global and local features to get more fine-grained features. However, these methods usually acquire local features with the help of human pose or segmentation models, which makes it difficult to use in realistic scenarios due to the introduction of additional models or complex training evaluation strategies. To facilitate practical applications, we propose a BERT-based framework for dual-path TI-ReID. Without the help of additional models, our approach directly employs visual attention in the global feature extraction network to allow the network to adaptively learn to focus on salient local features in image and text descriptions, which enhances the network’s attention to local information through a visual attention mechanism, thus strengthening the global feature representation and effectively improving the global feature representation. In addition, to learn text and image modality invariant feature representations, we propose a convolutional shared network (CSN) to learn image and text features together. To optimize cross-modal feature distances more effectively, we propose a global hybrid modal triplet global metric loss. In addition to combining local metric learning and global metric learning, we also introduce the CMPM loss and CMPC loss to jointly optimize the proposed model. Extensive experiments on the CUHK-PEDES dataset show that the proposed method performs significantly better than the current research results, achieving a Rank-1/mAP accuracy of 66.27%/ 57.04%.

Optimal multi-kernel SVM classifier with rotation, illumination and scale invariant hybrid DWT-Shearlet based GLCM feature descriptor and its application to face recognition

In computer vision, we must handle with the various structural aspects of image or video data. The texture is one of the most important aspects of this type of data, which is utilised to identify objects or regions of interest in an image. As imaging conditions change, textures inside actual images significantly change in brightness, contrast, size, and skew. To recognise textures in real-world images, a similarity measure that is invariant to these features must be used. Existing recognition techniques did not perform well due to issues such as illumination, scale, and subject rotation. To address this issue, invariant feature representation methods are being developed to generate features that are insensitive to such variations. In this paper, we proposed a robust hybrid feature descriptor and predicted the faces under illumination, scale, and pose variations using an optimum multi-kernel support vector machine. Additionally, the suggested robust hybrid feature descriptor is enhanced by combining a hybrid transform composed of discrete wavelet and discrete shearlet transforms with some image statistical textural data. The proposed face recognition system is implemented in MATLAB, and analysed using various parameters to show proposed methods improved performance as compared to the state of the art methods.

Unsupervised domain adaptation for the detection of cardiomegaly in cross-domain chest X-ray images.

In recent years, several deep learning approaches have been successfully applied in the field of medical image analysis. More specifically, different deep neural network architectures have been proposed and assessed for the detection of various pathologies based on chest X-ray images. While the performed assessments have shown very promising results, most of them consist in training and evaluating the performance of the proposed approaches on a single data set. However, the generalization of such models is quite limited in a cross-domain setting, since a significant performance degradation can be observed when these models are evaluated on data sets stemming from different medical centers or recorded under different protocols. The performance degradation is mostly caused by the domain shift between the training set and the evaluation set. To alleviate this problem, different unsupervised domain adaptation approaches are proposed and evaluated in the current work, for the detection of cardiomegaly based on chest X-ray images, in a cross-domain setting. The proposed approaches generate domain invariant feature representations by adapting the parameters of a model optimized on a large set of labeled samples, to a set of unlabeled images stemming from a different data set. The performed evaluation points to the effectiveness of the proposed approaches, since the adapted models outperform optimized models which are directly applied to the evaluation sets without any form of domain adaptation.

Robust Low-Rank Clustering Contrastive Learning Integrating Transformer for Noisy Industrial Soft Sensors

Strong process noise and disturbance caused by operating conditions and internal systems have brought a considerable challenge for soft sensor modeling in industrial processes. Existing modeling methods mainly focus on removing the noise from the process data, which do not improve the accuracy of the soft sensor model effectively for it is unrealistic to get completely noise-free data in actual industrial processes. Therefore, a novel robust Low-rank Clustering Contrastive Learning (LrCCL) integrating Transformer (LrCCL-T) is proposed in this paper. Based on the data augmentation technology, the LrCCL is designed to learn intrinsic and invariant feature representations from the process data by combining low-rank prior (Lr) and adaptive clustering contrastive learning (CCL). The CCL can bring closer the pairs from the same sample and cluster. Moreover, the Lr which assumes that samples in the same cluster should lie in a low-dimensional subspace is utilized to enhance the learned feature representations by adding a low-rank constraint. Then, the Transformer is used to build the soft sensor model, which can extract dynamic temporal relationship between the learned feature representations and outputs. Finally, to verify the effectiveness and robustness of the proposed method, a public industrial thermal power dataset and an actual industrial polypropylene dataset are utilized to build the steam volume (SV) and the melt index (MI) soft sensor model, respectively. The contrastive and ablation experiment results show that the proposed LrCCL-T can achieve comparable accuracy to other state-of-the-art soft sensor methods under strong noise industrial environment.

Adaptive Class Center Generalization Network: A Sparse Domain-Regressive Framework for Bearing Fault Diagnosis Under Unknown Working Conditions

Fault diagnosis is essential to ensure the bearing safety in the smart manufacturing. As the rotating bearings usually work under the variable working conditions, there may exist the differences between the data distributions of the training and test domains. Domain adaptation fault diagnosis (DAFD) has been adopted to handle with this domain shift phenomenon. But DAFD relies on the target domain heavily during its training process, while the target domain is always unavailable in real-world scenarios. To handle with this situation, this paper proposed a new adaptive class center generalization network (ACCGN). ACCGN is used to learn invariant feature representations of orientation signals from multiple source domains. First, ACCGN is used to learn the discriminative invariant fault feature from multi-source domains, and it combines the sparse domain regression framework and central loss to optimize the data features from inter- and intra-class simultaneously. Second, a new adaptive method is proposed to update the center in central loss and it can diminish the effect on the initialization center location. Third, a sparse domain regression framework is used to learn the inter-class invariant features. The proposed ACCGN has been tested on two famous bearing datasets, and the results have shown the effectiveness of the proposed ACCGN on the CWRU and JNU datasets.

An Intelligent Shooting Reward Learning Network Scheme for Medical Image Landmark Detection

As the need for medical services has grown in recent years, medical image critical point detection has emerged as a new subject of research for academics. In this paper, a search decision network method is proposed for medical image landmark detection. Unlike the conventional coarse-to-fine methods which generate bias prediction due to poor initialization, our method is to use the neural network structure search strategy to find a suitable network structure and then make reasonable decisions for robust prediction. To achieve this, we formulate medical landmark detection as a Markov decision process and design a shooting reward function to interact with the task. The task aims to maximize the discount of the received value and search for the optimal network architecture over the entire search space. Furthermore, we embed the central difference convolution, which typically extracts the data invariant feature representation, into the architectural search space. In experiments using standard accessible datasets, our approach achieves a detection accuracy of 98.59% in the 4 mm detection range. Our results demonstrate that, on standard datasets, our proposed approach consistently outperforms the majority of methods.

Texture classification with modified rotation invariant local binary pattern and gradient boosting

Since texture is prominent low level feature of an image, most of the image processing and computer vision applications rely on this feature for efficient extraction, retrieval, visualization and classification of the images. Hence, the texture analysis method mainly concentrates on efficient feature extraction and representation of the image. The images captured and analyzed in many of the applications are not in same (or) similar scale, orientation and illumination and also texture has regular, stochastic, periodic, homogeneous (or) inhomogeneous and directional in nature. To address these issues, recent texture analysis method focused on efficient and invariant feature extraction and representation with reduced dimension. Hence this paper proposes a invariant texture descriptor, Locality preserving Rotation Invariant Modified Directional Local Binary Pattern (LRIMDLBP) based on LBP. The classical LBP descriptor is widely used in most of the texture analysis applications due to its simplicity and robustness to illumination changes. However, it does not efficiently capture the discriminative texture information because it uses sign information and ignores the magnitude value of the neighborhood and also suffers from high dimensionality. Hence to improve the performance of LBP, many variants are proposed. Though most of these LBP variants are either geometrical or direction invariant, fails to address the spatial locality and contrast invariance. To address these issues, the proposed LRIMDLBP incorporates spatial locality, contrast and direction information for rotation invariant texture descriptor with reduced dimension. The proposed LRIMDLBP consists of 5 phases: (i) Reference point identification, (ii) Magnitude calculation, (iii) Binary Label computation based on threshold, (iv) Pattern identification in dominant direction and (v) LRIMDLBP code computation. The locality and rotation invariance is achieved by identifying and using reference point in a local neighborhood. The reference point is a dominant pixel whose magnitude is large in the neighborhood excluding center pixel. The spatial locality and rotation invariance is achieved by preserving the weights of LBP dynamically based on the reference point. The proposed method also preserves the direction information of the texture by comparing the magnitude of the pixel in the four dominant directions such as horizontal, vertical, diagonal and anti-diagonal directions. Finally the proposed invariant LRIMDLBP descriptor computes histogram based on decimal pattern value. The proposed LRIMDLBP descriptor results in texture feature with reduced dimension when compared to other LBP variants. The performance of the proposed descriptor is evaluated with large and well known four bench mark texture datasets namely (i) CUReT, (ii) Outex, (iii) KTS-TIPS and (iv) UIUC against three classifiers such as (i). K-Nearest Neighbor (K-NN), (ii). Support Vector Machine (SVM) with Radial Basis Function (RBF) and (iii). Gradient Boosting Classifier (GBC). The intensive experimental result shows that the ensemble based GBC yields superior classification accuracy of 99.38%, 99.43%, 98.67% and 98.82% for the datasets CUReT, Outex, KTH-TIPS and UIUC respectively when compared with other two classifiers and also improves the generalization ability. The proposed LRIMDLBP descriptor achieves approximately 15% more classification accuracy when compared with traditional LBP and also produces 1% to 2.5% more classification accuracy compared with other state of the art LBP variants.

OACNNs: Orientation adaptive convolutional neural networks

Geometric invariant feature representation plays an indispensable role in the field of image processing and computer vision. Recently, convolution neural networks (CNNs) have witnessed a great research progress, however CNNs do not excel at dealing with geometrically transformed images. Existing methods enhancing the ability of CNNs learning invariant feature representation rely partly on data augmentation or have a relatively weak generalization ability. This paper proposes orientation adaptive kernels (OA kernels) and orientation adaptive max pooling (OA max pooling) that comprise a new topological structure, orientation adaptive neural networks (OACNNs). OA kernels output the orientation feature maps which encode the orientation information of images. OA max pooling max-pools the orientation feature maps by automatically rotating the pooling windows according to their orientation. OA kernels and OA max pooling together allow for the eight orientation response of images to be computed, and then the max orientation response is obtained, which is proved to be a robust rotation invariant feature representation. OACNNs are compared with state-of-the-art methods and consistently outperform them in various experiments. OACNNs demonstrate a better generalization ability, yielding a test error rate 3.14 on the rotated images but only trained on “up-right” images, which outperforms all state-of-the-art methods by a large margin.

Learning invariant representation for unsupervised domain adaptive thorax disease classification

• It designs a novel UDA framework that learns invariant features for optimizing thorax disease classification . • We propose a novel feature learning scheme that regularizes features concurrently via three types of invariance constraints. • We develop an end-to-end trainable deep network that significantly improves the thorax disease classification performance. Unsupervised Domain Adaptation (UDA) based thorax disease classification is a challenging task due to the data distribution discrepancy between source and target domains, and the lack of labeling information in target domain. In this paper, we present an innovative UDA framework that learns invariant and discriminative feature representations from Chest X-rays (CXR) images for UDA-based thorax disease classification across domains. Specifically, a Convolutional Neural Network (CNN) is adopted that explicitly learns discriminative feature representation from CXR images under the supervision of a labeled source domain. A domain-invariance constraint is designed to further align feature distributions between the labeled source domain and the unlabeled target domain. In addition, an instance-invariance constraint and a perturbation-invariance constraint are designed that guide the learning to capture robust and discriminative features from target CXR images. The proposed method has been evaluated on the ChestX-ray14 and SYSU datasets and the experimental results demonstrate its superior robustness and effectiveness relative to state-of-the-art approaches.

Apparel-Invariant Feature Learning for Person Re-Identification

With the rise of deep learning methods, person Re-Identification (ReID) performance has been improved tremendously in many public datasets. However, most public ReID datasets are collected in a short time window in which persons’ appearance rarely changes. In real-world applications such as in a shopping mall, the same person may change their wearings, and different persons may wear similar apparel. It reveals a critical problem that current ReID models heavily rely on a person’s apparel, resulting in an inconsistent ReID performance. Therefore, it is crucial to learn an apparel-invariant person representation under clothes changing or several persons wearing similar clothes cases. In this work, we tackle this problem from the viewpoint of invariant feature representation learning. The main contributions of this work are as follows. (1) We propose the semi-supervised Apparel-invariant Feature Learning (AIFL) framework to learn an apparel-invariant pedestrian representation using images of the same person wearing different clothes. (2) To obtain images of the same person wearing different clothes, we propose an unsupervised apparel-simulation GAN (AS-GAN) to synthesize cloth-changing images according to the target cloth embedding. It is worth noting that the images used in ReID tasks were cropped from real-world low-quality CCTV videos, making it more challenging to synthesize cloth-changing images. Extensive experiments demonstrate that our proposal can improve the ReID performance of the baseline models.

Weighted Conditional Discriminant Analysis for Unseen Operating Modes Fault Diagnosis in Chemical Processes

One challenge faced by data-driven fault diagnosis methods is that they may perform well over the operating modes where the historical data are collected, but fail to generalize to unseen modes that have never appeared before. That is one of the root causes that have prevented many advanced fault diagnosis methods from being widely accepted by the chemical industry. Consequently, it is significant to develop a novel fault diagnosis method, which can build a model to determine the type of faults occurred on unseen modes. On the other hand, one chemical process generally experiences multiple operating modes, from which common knowledge of these modes can be extracted and be applied to an unseen mode. To this end, a novel weighted conditional discriminant analysis (WCDA) algorithm is proposed by adopting the context of domain generalization (DG) approaches to leverage and distill the knowledge from historical modes for unseen modes of fault diagnosis. Specifically, a novel variable weighting scheme is developed based on the Kullback–Leibler divergence between features of different modes. Then, a fault diagnosis model is constructed by learning a classifier and invariant feature representation simultaneously. Moreover, WCDA is extended to the context of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">domain adaptation</i> (DA), where the performance of the fault diagnosis model is further improved by leveraging the unlabeled data collected from a new mode. Empirical results on a numerical example, the Tennessee Eastman process, and continuous stirred tank chemical reactor demonstrate the effectiveness of our method.

Pivot-Guided Embedding for Domain Generalization

Neural networks have suffered from a distribution gap between training and test data, known as domain shift. Domain generalization (DG) methods aim to learn domain invariant representations only with limited source domain data to cope with unseen target domains. The main assumption is that the model trained to extract semantically consistent features without any domain specific information is highly adaptable to the unseen target domain. Metric learning allows embedding representations to be class-separated and domain-mixed, which is an optimal condition for DG but has been downplayed in recent works. Even the most popular triplet embedding has limitations in forming an optimal embedding space for DG due to instability. In this paper, we present a novel deep metric learning method for domain invariant representations. Specifically, we propose Pivot-Guided Embedding (PGE), which explicitly forms the entire feature distribution of the embedding space with a novel pivot-guided attraction-repulsion mechanism, to address the instability problem that triplet embedding has. In particular, we leverage pivot features representing a coarse distribution of the entire space as reference points to guide other features toward domain invariant feature distribution. To this end, a pivot selection algorithm is presented to reliably reflect the entire feature distribution. Furthermore, we define Guide-Field, a subspace spanned by a subset of pivots chosen for individual samples, to guide each sample to domain invariant feature space. In a nutshell, the attraction-repulsion mechanism based on pivots, the reliable set of features representing the entire feature distribution, enables the model to extract domain invariant feature representations and also settles the instability problem of triplet loss. Experimental results on three different benchmarks validate the performance advantages of the proposed method over the state-of-the-art DG techniques.

Network Intrusion Detection Model Based on Improved BYOL Self-Supervised Learning

The combination of deep learning and intrusion detection has become a hot topic in today’s network security. In the face of massive, high-dimensional network traffic with uneven sample distribution, how to be able to accurately detect anomalous traffic is the primary task of intrusion detection. Most research on intrusion detection systems based on network anomalous traffic detection has focused on supervised learning; however, the process of obtaining labeled data often requires a lot of time and effort, as well as the support of network experts. Therefore, it is worthwhile investigating the development of label-free self-supervised learning-based approaches called BYOL which is a simple and elegant framework with sufficiently powerful feature extraction capabilities for intrusion detection systems. In this paper, we propose a new data augmentation strategy for intrusion detection data and an intrusion detection model based on label-free self-supervised learning, using a new data augmentation strategy to introduce a perturbation enhancement model to learn invariant feature representation capability and an improved BYOL self-supervised learning method to train the UNSW-NB15 intrusion detection dataset without labels to extract network traffic feature representations. Linear evaluation on UNSW-NB15 and transfer learning on NSK-KDD, KDD CUP99, CIC IDS2017, and CIDDS_001 achieve excellent performance in all metrics.

Spacecraft Intelligent Fault Diagnosis under Variable Working Conditions via Wasserstein Distance-Based Deep Adversarial Transfer Learning

In recent years, deep learning methods which promote the accuracy and efficiency of fault diagnosis task without any extra requirement of artificial feature extraction have elicited the attention of researchers in the field of manufacturing industry as well as aerospace. However, the problems that data in source and target domains usually have different probability distributions because of different working conditions and there are insufficient labeled or even unlabeled data in target domain significantly deteriorate the performance and generalization of deep fault diagnosis models. To address these problems, we propose a novel Wasserstein Generative Adversarial Network with Gradient Penalty- (WGAN-GP-) based deep adversarial transfer learning (WDATL) model in this study, which exploits a domain critic to learn domain invariant feature representations by minimizing the Wasserstein distance between the source and target feature distributions through adversarial training. Moreover, an improved one-dimensional convolutional neural network- (CNN-) based feature extractor which utilizes exponential linear units (ELU) as activation functions and wide kernels is designed to automatically extract the latent features of raw time-series input data. Then, the fault model classifier trained in one working condition (source domain) with sufficient labeled samples could be generalized to diagnose data in other working conditions (target domain) with insufficient labeled samples. Experiments on two open datasets demonstrate that our proposed WDATL model outperforms most of the state-of-the-art approaches on transfer diagnosis tasks under diverse working circumstances.

DF-Net: Deep fusion network for multi-source vessel segmentation

Accurate retinal vessel segmentation is very challenging. Recently, the deep learning based method has greatly improved performance. However, the non-vascular structures usually harm the performance and some low contrast small vessels are hard to be detected after several down-sampling operations. To solve these problems, we design a deep fusion network (DF-Net) including multiscale fusion, feature fusion and classifier fusion for multi-source vessel image segmentation. The multiscale fusion module allows the network to detect blood vessels with different scales. The feature fusion module fuses deep features with vessel responses extracted from a Frangi filter to obtain a compact yet domain invariant feature representation. The classifier fusion module provides the network more supervision. DF-Net also predicts the parameter of the Frangi filter to avoid manually picking the best parameters. The learned Frangi filter enhances the feature map of the multiscale network and restores the edge information loss caused by down-sampling operations. The proposed end-to-end network is easy to train and the inference time for one image is 41ms on a GPU. The model outperforms state-of-the-art methods and achieves the accuracy of 96.14%, 97.04%, 98.02% from three publicly available fundus image datasets DRIVE, STARE, CHASEDB1, respectively. The code is available at https://github.com/y406539259/DF-Net.

Scene Coordinate Regression Network With Global Context-Guided Spatial Feature Transformation for Visual Relocalization

Among visual relocalization from a single RGB image, the scene coordinate regression (SCoRe) based on convolutional neural network (CNN) becomes prevailing, however, it is insufficient to extract invariant features under different viewpoints due to fixed geometric structures of CNN. In this letter, we propose a global context-guided spatial feature transformation (SFT) network to learn invariant feature representation for robustness against viewpoint changes. Specifically, global feature extracted from source feature map is regarded as a dynamic convolutional kernel, which is convolved with source feature map for the prediction of transformation parameters. The predicted parameters are used to transform features of multiple viewpoints to a canonical space with the constraint of maximum likelihood-derived loss, and thus viewpoint invariance is achieved. CoordConv is also employed to further improve the discrimination of features on texture-less or repetitive zones. The proposed SFT network can be easily incorporated into the general SCoRe network. To our best knowledge, features are first decoupled from viewpoints explicitly in SCoRe network by the spatial feature transformation network, which achieves a stable and accurate visual relocalization. The experimental results demonstrate the effectiveness of the proposed method in terms of accuracy and efficiency.

Interpatient ECG Heartbeat Classification with an Adversarial Convolutional Neural Network.

Discovering shared, invariant feature representations across subjects in electrocardiogram (ECG) classification tasks is crucial for improving the generalization of models to unknown patients. Although deep neural networks have recently been emerging in extracting generalizable ECG features, they usually rely on labeled samples from a large number of subjects to guarantee generalization. Extracting invariant representations to intersubject variabilities from a small number of subjects is still a challenge today due to individual physical differences. To address this problem, we propose an adversarial deep neural network framework for interpatient heartbeat classification by integrating adversarial learning into a convolutional neural network to learn subject-invariant, class-discriminative features. The proposed method was evaluated on the MIT-BIH arrhythmia database which is a publicly available ECG dataset collected from 47 patients. Compared with the state-of-the-art methods, the proposed method achieves the highest performance for detecting supraventricular ectopic beats (SVEBs), which are very challenging to identify, and also gains comparable performance on the detection of ventricular ectopic beats (VEBs). The sensitivities of SVEBs and VEBs are 78.8% and 92.5%, respectively. The precisions of SVEBs and VEBs are 90.8% and 94.3%, respectively. With high performance in the detection of pathological classes (i.e., SVEBs and VEBs), this work provides a promising method for ECG classification tasks when the number of patients is limited.