Search

This paper proposes a novel end-to-end learning model, called skip-connected covariance (SCCov) network, for remote sensing scene classification (RSSC). The innovative contribution of this paper is to embed two novel modules into the traditional convolutional neural network (CNN) model, i.e., skip connections and covariance pooling. The advantages of newly developed SCCov are twofold. First, by means of the skip connections, the multi-resolution feature maps produced by the CNN are combined together, which provides important benefits to address the presence of large-scale variance in RSSC data sets. Second, by using covariance pooling, we can fully exploit the second-order information contained in such multi-resolution feature maps. This allows the CNN to achieve more representative feature learning when dealing with RSSC problems. Experimental results, conducted using three large-scale benchmark data sets, demonstrate that our newly proposed SCCov network exhibits very competitive or superior classification performance when compared with the current state-of-the-art RSSC techniques, using a much lower amount of parameters. Specifically, our SCCov only needs 10% of the parameters used by its counterparts. [ABSTRACT FROM AUTHOR]

Semisupervised text classification has attracted much attention from the research community. In this paper, a novel model, the semisupervised sequential variational autoencoder (SSVAE), is proposed to tackle this problem. By treating the categorical label of unlabeled data as a discrete latent variable, the proposed model maximizes the variational evidence lower bound of the data likelihood, which implicitly derives the underlying label distribution for the unlabeled data. Analytical work indicates that the autoregressive nature of the sequential model is the crucial issue that renders the vanilla model ineffective. To remedy this, two types of decoders are investigated in the SSVAE model and verified. In addition, a reweighting approach is proposed to circumvent the credit assignment problem that occurs during the reconstruction procedure, which can further improve performance for sparse text data. Experimental results show that our method significantly improves the classification accuracy compared with other modern methods. [ABSTRACT FROM AUTHOR]

Linear discriminant analysis (LDA) is a well-known technique for linear classification, feature extraction, and dimension reduction. To improve the accuracy of LDA under the high dimension low sample size (HDLSS) settings, shrunken estimators, such as Graphical Lasso, can be used to strike a balance between biases and variances. Although the estimator with induced sparsity obtains a faster convergence rate, however, the introduced bias may also degrade the performance. In this paper, we theoretically analyze how the sparsity and the convergence rate of the precision matrix (also known as inverse covariance matrix) estimator would affect the classification accuracy by proposing an analytic model on the upper bound of an LDA misclassification rate. Guided by the model, we propose a novel classifier, $\mathcal {DBSDA}$ , which improves classification accuracy through debiasing. Theoretical analysis shows that $\mathcal {DBSDA}$ possesses a reduced upper bound of misclassification rate and better asymptotic properties than sparse LDA (SDA). We conduct experiments on both synthetic datasets and real application datasets to confirm the correctness of our theoretical analysis and demonstrate the superiority of $\mathcal {DBSDA}$ over LDA, SDA, and other downstream competitors under HDLSS settings. [ABSTRACT FROM AUTHOR]

Many real-world classification problems are characterized by samples of a complex distribution in the input space. The classification accuracy is determined by intrinsic properties of all samples in subspaces of features. This paper proposes a novel algorithm for the construction of radial basis function neural network (RBFNN) classifier based on subspace learning. In this paper, feature subspaces are obtained for every hidden node of the RBFNN during the learning process. The connection weights between the input layer and the hidden layer are adjusted to produce various subspaces with dominative features for different hidden nodes. The network structure and dominative features are encoded in two subpopulations that are cooperatively coevolved using the coevolutionary algorithm to achieve a better global optimality for the estimated RBFNN. Experimental results illustrate that the proposed algorithm is able to obtain RBFNN models with both better classification accuracy and simpler network structure when compared with other learning algorithms. Thus, the proposed model provides a more flexible and efficient approach to complex classification tasks by employing the local characteristics of samples in subspaces. [ABSTRACT FROM PUBLISHER]

Linear dynamical system (LDS) offers a convenient way to reveal the unobservable structure behind the data. This makes it useful for data representation and explanatory analysis. An immediate limitation with this model is that most training algorithms train a model to best approximate a sequential instance. They do not consider its class or label which indicates the dissimilarity/similarity to other instances. As a result, LDS’s trained in this way are inclined to be indistinguishable over classes, resulting in a poor performance in the model-based classification. In this paper, after revisiting this limitation, we propose to promote the diversity between the two models of different classes. The diversity, measured by determinantal point process (DPP) on LDS’s, is utilized to remedy the greedy behavior of the electromagnetic algorithm. The training goal is a model that balances the goodness of fit and being distinguishable over classes. Experiments on synthetic data confirm its effectiveness in generating discriminative systems under supervisory information. The classification on short time-span data sets confirms that the models generated by our approach could generalize well to unseen data. [ABSTRACT FROM AUTHOR]

The objective of this paper is the design of an engine for the automatic generation of supervised manifold embedding models. It proposes a modular and adaptive data embedding framework for classification, referred to as DEFC, which realizes in different stages including initial data preprocessing, relation feature generation and embedding computation. For the computation of embeddings, the concepts of friend closeness and enemy dispersion are introduced, to better control at local level the relative positions of the intraclass and interclass data samples. These are shown to be general cases of the global information setup utilized in the Fisher criterion, and are employed for the construction of different optimization templates to drive the DEFC model generation. For model identification, we use a simple but effective bilevel evolutionary optimization, which searches for the optimal model and its best model parameters. The effectiveness of DEFC is demonstrated with experiments using noisy synthetic datasets possessing nonlinear distributions and real-world datasets from different application fields. [ABSTRACT FROM AUTHOR]

Transfer learning becomes an attractive technology to tackle a task from a target domain by leveraging previously acquired knowledge from a similar domain (source domain). Many existing transfer learning methods focus on learning one discriminator with single-source domain. Sometimes, knowledge from single-source domain might not be enough for predicting the target task. Thus, multiple source domains carrying richer transferable information are considered to complete the target task. Although there are some previous studies dealing with multi-source domain adaptation, these methods commonly combine source predictions by averaging source performances. Different source domains contain different transferable information; they may contribute differently to a target domain compared with each other. Hence, the source contribution should be taken into account when predicting a target task. In this article, we propose a novel multi-source contribution learning method for domain adaptation (MSCLDA). As proposed, the similarities and diversities of domains are learned simultaneously by extracting multi-view features. One view represents common features (similarities) among all domains. Other views represent different characteristics (diversities) in a target domain; each characteristic is expressed by features extracted in a source domain. Then multi-level distribution matching is employed to improve the transferability of latent features, aiming to reduce misclassification of boundary samples by maximizing discrepancy between different classes and minimizing discrepancy between the same classes. Concurrently, when completing a target task by combining source predictions, instead of averaging source predictions or weighting sources using normalized similarities, the original weights learned by normalizing similarities between source and target domains are adjusted using pseudo target labels to increase the disparities of weight values, which is desired to improve the performance of the final target predictor if the predictions of sources exist significant difference. Experiments on real-world visual data sets demonstrate the superiorities of our proposed method. [ABSTRACT FROM AUTHOR]

Efficient modeling of feature interactions underpins supervised learning for nonsequential tasks, characterized by a lack of inherent ordering of features (variables). The brute force approach of learning a parameter for each interaction of every order comes at an exponential computational and memory cost (curse of dimensionality). To alleviate this issue, it has been proposed to implicitly represent the model parameters as a tensor, the order of which is equal to the number of features; for efficiency, it can be further factorized into a compact tensor train (TT) format. However, both TT and other tensor networks (TNs), such as tensor ring and hierarchical Tucker, are sensitive to the ordering of their indices (and hence to the features). To establish the desired invariance to feature ordering, we propose to represent the weight tensor through the canonical polyadic (CP) decomposition (CPD) and introduce the associated inference and learning algorithms, including suitable regularization and initialization schemes. It is demonstrated that the proposed CP-based predictor significantly outperforms other TN-based predictors on sparse data while exhibiting comparable performance on dense nonsequential tasks. Furthermore, for enhanced expressiveness, we generalize the framework to allow feature mapping to arbitrarily high-dimensional feature vectors. In conjunction with feature vector normalization, this is shown to yield dramatic improvements in performance for dense nonsequential tasks, matching models such as fully connected neural networks. [ABSTRACT FROM AUTHOR]

Feature point recognition is a key component in many vision-based applications, such as vision-based robot navigation, object recognition and classification, image-based modeling, and augmented reality. Real-time performance and high recognition rates are of crucial importance to these applications. In this brief, we propose a novel method for real-time keypoint recognition using restricted Boltzmann machine (RBM). RBMs are generative models that can learn probability distributions of many different types of data including labeled and unlabeled data sets. Due to the inherent noise of the training data sets, we use an RBM to model statistical distributions of the training data. Furthermore, the learned RBM can be used as a competitive classifier to recognize the keypoints in real-time during the tracking stage, thus making it advantageous to be employed in applications that require real-time performance. Experiments have been conducted under a variety of conditions to demonstrate the effectiveness and generalization of the proposed approach. [ABSTRACT FROM PUBLISHER]

The problem of effectively exploiting the information multiple data sources has become a relevant but challenging research topic in remote sensing. In this article, we propose a new approach to exploit the complementarity of two data sources: hyperspectral images (HSIs) and light detection and ranging (LiDAR) data. Specifically, we develop a new dual-channel spatial, spectral and multiscale attention convolutional long short-term memory neural network (called dual-channel $A^{3}$ CLNN) for feature extraction and classification of multisource remote sensing data. Spatial, spectral, and multiscale attention mechanisms are first designed for HSI and LiDAR data in order to learn spectral- and spatial-enhanced feature representations and to represent multiscale information for different classes. In the designed fusion network, a novel composite attention learning mechanism (combined with a three-level fusion strategy) is used to fully integrate the features in these two data sources. Finally, inspired by the idea of transfer learning, a novel stepwise training strategy is designed to yield a final classification result. Our experimental results, conducted on several multisource remote sensing data sets, demonstrate that the newly proposed dual-channel $A^{\,3}$ CLNN exhibits better feature representation ability (leading to more competitive classification performance) than other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Multilabel learning has been extensively studied in the past years, as it has many applications in different domains. It aims at annotating the labels for unseen data according to training data, which are often high dimensional in both instance and feature levels. The training data often have noisy and redundant information on these two levels. As an effective data preprocessing step, instance and feature selection should both be performed to find relevant training instances for each testing instance and relevant features for each label, respectively. However, most of the existing methods overlook the input–output correlation in each kind of selection. It will lead to the performance degradation. This article presents a formulation for multilabel learning from a topic view that exploits the dependence between features and labels in a topic space. We can perform effective instance and feature selection in the latent topic space, as the relationship between the input and output spaces is well captured in this space. The results from intensive experiments on various benchmarks demonstrate the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]

The early and reliable detection of COVID-19 infected patients is essential to prevent and limit its outbreak. The PCR tests for COVID-19 detection are not available in many countries, and also, there are genuine concerns about their reliability and performance. Motivated by these shortcomings, this article proposes a deep uncertainty-aware transfer learning framework for COVID-19 detection using medical images. Four popular convolutional neural networks (CNNs), including VGG16, ResNet50, DenseNet121, and InceptionResNetV2, are first applied to extract deep features from chest X-ray and computed tomography (CT) images. Extracted features are then processed by different machine learning and statistical modeling techniques to identify COVID-19 cases. We also calculate and report the epistemic uncertainty of classification results to identify regions where the trained models are not confident about their decisions (out of distribution problem). Comprehensive simulation results for X-ray and CT image data sets indicate that linear support vector machine and neural network models achieve the best results as measured by accuracy, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC). Also, it is found that predictive uncertainty estimates are much higher for CT images compared to X-ray images. [ABSTRACT FROM AUTHOR]

For a target task where the labeled data are unavailable, domain adaptation can transfer a learner from a different source domain. Previous deep domain adaptation methods mainly learn a global domain shift, i.e., align the global source and target distributions without considering the relationships between two subdomains within the same category of different domains, leading to unsatisfying transfer learning performance without capturing the fine-grained information. Recently, more and more researchers pay attention to subdomain adaptation that focuses on accurately aligning the distributions of the relevant subdomains. However, most of them are adversarial methods that contain several loss functions and converge slowly. Based on this, we present a deep subdomain adaptation network (DSAN) that learns a transfer network by aligning the relevant subdomain distributions of domain-specific layer activations across different domains based on a local maximum mean discrepancy (LMMD). Our DSAN is very simple but effective, which does not need adversarial training and converges fast. The adaptation can be achieved easily with most feedforward network models by extending them with LMMD loss, which can be trained efficiently via backpropagation. Experiments demonstrate that DSAN can achieve remarkable results on both object recognition tasks and digit classification tasks. Our code will be available at https://github.com/easezyc/deep-transfer-learning. [ABSTRACT FROM AUTHOR]

We introduce a deep imbalanced learning framework called learning DEep Landmarks in laTent spAce (DELTA). Our work is inspired by the shallow imbalanced learning approaches to rebalance imbalanced samples before feeding them to train a discriminative classifier. Our DELTA advances existing works by introducing the new concept of rebalancing samples in a deeply transformed latent space, where latent points exhibit several desired properties including compactness and separability. In general, DELTA simultaneously conducts feature learning, sample rebalancing, and discriminative learning in a joint, end-to-end framework. The framework is readily integrated with other sophisticated learning concepts including latent points oversampling and ensemble learning. More importantly, DELTA offers the possibility to conduct imbalanced learning with the assistancy of structured feature extractor. We verify the effectiveness of DELTA not only on several benchmark data sets but also on more challenging real-world tasks including click-through-rate (CTR) prediction, multi-class cell type classification, and sentiment analysis with sequential inputs. [ABSTRACT FROM AUTHOR]

The positive-unlabeled (PU) classification is a common scenario in real-world applications such as healthcare, text classification, and bioinformatics, in which we only observe a few samples labeled as “positive” together with a large volume of “unlabeled” samples that may contain both positive and negative samples. Building robust classifiers for the PU problem is very challenging, especially for complex data where the negative samples overwhelm and mislabeled samples or corrupted features exist. To address these three issues, we propose a robust learning framework that unifies area under the curve maximization (a robust metric for biased labels), outlier detection (for excluding wrong labels), and feature selection (for excluding corrupted features). The generalization error bounds are provided for the proposed model that give valuable insight into the theoretical performance of the method and lead to useful practical guidance, e.g., to train a model, we find that the included unlabeled samples are sufficient as long as the sample size is comparable to the number of positive samples in the training process. Empirical comparisons and two real-world applications on surgical site infection (SSI) and EEG seizure detection are also conducted to show the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Despite the great success of convolutional neural networks (CNNs) for the image classification task on data sets such as Cifar and ImageNet, CNN’s representation power is still somewhat limited in dealing with images that have a large variation in size and clutter, where Fisher vector (FV) has shown to be an effective encoding strategy. FV encodes an image by aggregating local descriptors with a universal generative Gaussian mixture model (GMM). FV, however, has limited learning capability and its parameters are mostly fixed after constructing the codebook. To combine together the best of the two worlds, we propose in this brief a neural network structure with FV layer being part of an end-to-end trainable system that is differentiable; we name our network FisherNet that is learnable using back propagation. Our proposed FisherNet combines CNN training and FV encoding in a single end-to-end structure. We observe a clear advantage of FisherNet over plain CNN and standard FV in terms of both classification accuracy and computational efficiency on the challenging PASCAL visual object classes object classification and emotion image classification tasks. [ABSTRACT FROM AUTHOR]

Real-world data are often acquired as a collection of matrices rather than as a single matrix. Such multiblock data are naturally linked and typically share some common features while at the same time exhibiting their own individual features, reflecting the underlying data generation mechanisms. To exploit the linked nature of data, we propose a new framework for common and individual feature extraction (CIFE) which identifies and separates the common and individual features from the multiblock data. Two efficient algorithms termed common orthogonal basis extraction (COBE) are proposed to extract common basis is shared by all data, independent on whether the number of common components is known beforehand. Feature extraction is then performed on the common and individual subspaces separately, by incorporating dimensionality reduction and blind source separation techniques. Comprehensive experimental results on both the synthetic and real-world data demonstrate significant advantages of the proposed CIFE method in comparison with the state-of-the-art. [ABSTRACT FROM AUTHOR]

Decision trees are widely used predictive models in machine learning. Recently, $K$ -tree is proposed, where the original discrete feature space is expanded by generating all orderings of values of $k$ discrete attributes and these orderings are used as the new attributes in decision tree induction. Although $K$ -tree performs significantly better than the proper one, their exponential time complexity can prohibit their use. In this brief, we propose $K$ -forest, an extension of random forest, where a subset of features is selected randomly from the induced discrete space. Simulation results on 17 data sets show that the novel ensemble classifier has significantly lower error rate compared with the random forest based on the original feature space. [ABSTRACT FROM AUTHOR]