Large-Scale Image Retrieval with Deep Attentive Global Features

How to obtain discriminative features has proved to be a core problem for image retrieval. Many recent works use convolutional neural networks to extract features. However, clutter and occlusion will interfere with the distinguishability of features when using convolutional neural network (CNN) for feature extraction. To address this problem, we intend to obtain high-response activations in the feature map based on the attention mechanism. We propose two attention modules, a spatial attention module and a channel attention module. For the spatial attention module, we first capture the global information and model the relation between channels as a region evaluator, which evaluates and assigns new weights to local features. For the channel attention module, we use a vector with trainable parameters to weight the importance of each feature map. The two attention modules are cascaded to adjust the weight distribution for the feature map, which makes the extracted features more discriminative. Furthermore, we present a scale and mask scheme to scale the major components and filter out the meaningless local features. This scheme can reduce the disadvantages of the various scales of the major components in images by applying multiple scale filters, and filter out the redundant features with the MAX-Mask. Exhaustive experiments demonstrate that the two attention modules are complementary to improve performance, and our network with the three modules outperforms the state-of-the-art methods on four well-known image retrieval datasets.

A Sentiment Analysis Anomaly Detection System for Cyber Intelligence

Considering the 2030 United Nations intent of world connection, Cyber Intelligence becomes the main area of the human dimension able of inflicting changes in geopolitical dynamics. In cyberspace, the new battlefield is the mind of people including new weapons like abuse of social media with information manipulation, deception by activists and misinformation. In this paper, a Sentiment Analysis system with Anomaly Detection (SAAD) capability is proposed. The system, scalable and modular, uses an OSINT-Deep Learning approach to investigate on social media sentiment in order to predict suspicious anomaly trend in Twitter posts. Anomaly detection is investigated with a new semi-supervised process that is able to detect potentially dangerous situations in critical areas. The main contributions of the paper are the system suitability for working in different areas and domains, the anomaly detection procedure in sentiment context and a time-dependent confusion matrix to address model evaluation with unbalanced dataset. Real experiments and tests were performed on Sahel Region. The detected anomalies in negative sentiment have been checked by experts of Sahel area, proving true links between the models results and real situations observable from the tweets.

Developing an Anomaly Detection System for Automatic Defective Products’ Inspection

Since unqualified products cause enterprise revenue losses, product inspection is essential for maintaining manufacturing quality. An automated optical inspection (AOI) system is an efficient tool for product inspection, providing a convenient interface for users to view their products of interest. Specifically, in the screw manufacturing industry, the conventional methods are the human visual inspection of the product and for the inspector to view the product image displayed on the dashboard of the AOI system. However, despite the inspector and the approach used, inspection results strongly depend on the inspector’s experience. Moreover, machine learning algorithms could improve the efficiency of human visual inspection, thus addressing the above problem. Based on these facts, we improved anomaly detection efficiency during product inspection, using product image data from the AOI system to obtain valuable information. This study notably used the visual geometry group network, Inception V3, and Xception algorithms to detect qualified and unqualified products during product image analytics. Therefore, we considered that the analyzed results could be integrated into a proposed cloud system for human–machine interaction. Thus, administrators can receive reminders concerning the anomaly-inspected notification through the proposed cloud system, comprising a message queuing telemetry transport protocol, an application programming interface, and a cloud dashboard. From the experimental results, the above-mentioned algorithms had more than 93% accuracy, especially Xception, which had a better performance during the defective type classification. From our study, the proposed system can successfully apply the obtained data in data communication, anomaly dashboards, and anomaly notifications.

Human Silhouette and Skeleton Video Synthesis Through Wi-Fi signals

The increasing availability of wireless access points (APs) is leading toward human sensing applications based on Wi-Fi signals as support or alternative tools to the widespread visual sensors, where the signals enable to address well-known vision-related problems such as illumination changes or occlusions. Indeed, using image synthesis techniques to translate radio frequencies to the visible spectrum can become essential to obtain otherwise unavailable visual data. This domain-to-domain translation is feasible because both objects and people affect electromagnetic waves, causing radio and optical frequencies variations. In the literature, models capable of inferring radio-to-visual features mappings have gained momentum in the last few years since frequency changes can be observed in the radio domain through the channel state information (CSI) of Wi-Fi APs, enabling signal-based feature extraction, e.g. amplitude. On this account, this paper presents a novel two-branch generative neural network that effectively maps radio data into visual features, following a teacher-student design that exploits a cross-modality supervision strategy. The latter conditions signal-based features in the visual domain to completely replace visual data. Once trained, the proposed method synthesizes human silhouette and skeleton videos using exclusively Wi-Fi signals. The approach is evaluated on publicly available data, where it obtains remarkable results for both silhouette and skeleton videos generation, demonstrating the effectiveness of the proposed cross-modality supervision strategy.

VPNET: Variable Projection Networks

In this paper, we introduce VPNet, a novel model-driven neural network architecture based on variable projection (VP). Applying VP operators to neural networks results in learnable features, interpretable parameters, and compact network structures. This paper discusses the motivation and mathematical background of VPNet and presents experiments. The VPNet approach was evaluated in the context of signal processing, where we classified a synthetic dataset and real electrocardiogram (ECG) signals. Compared to fully connected and one-dimensional convolutional networks, VPNet offers fast learning ability and good accuracy at a low computational cost of both training and inference. Based on these advantages and the promising results obtained, we anticipate a profound impact on the broader field of signal processing, in particular on classification, regression and clustering problems.

Arbitrary Scale Super-Resolution for Medical Images

Single image super-resolution (SISR) aims to obtain a high-resolution output from one low-resolution image. Currently, deep learning-based SISR approaches have been widely discussed in medical image processing, because of their potential to achieve high-quality, high spatial resolution images without the cost of additional scans. However, most existing methods are designed for scale-specific SR tasks and are unable to generalize over magnification scales. In this paper, we propose an approach for medical image arbitrary-scale super-resolution (MIASSR), in which we couple meta-learning with generative adversarial networks (GANs) to super-resolve medical images at any scale of magnification in [Formula: see text]. Compared to state-of-the-art SISR algorithms on single-modal magnetic resonance (MR) brain images (OASIS-brains) and multi-modal MR brain images (BraTS), MIASSR achieves comparable fidelity performance and the best perceptual quality with the smallest model size. We also employ transfer learning to enable MIASSR to tackle SR tasks of new medical modalities, such as cardiac MR images (ACDC) and chest computed tomography images (COVID-CT). The source code of our work is also public. Thus, MIASSR has the potential to become a new foundational pre-/post-processing step in clinical image analysis tasks such as reconstruction, image quality enhancement, and segmentation.

One-Shot Neural Architecture Search by Dynamically Pruning Supernet in Hierarchical Order

Neural Architecture Search (NAS), which aims at automatically designing neural architectures, recently draw a growing research interest. Different from conventional NAS methods, in which a large number of neural architectures need to be trained for evaluation, the one-shot NAS methods only have to train one supernet which synthesizes all the possible candidate architectures. As a result, the search efficiency could be significantly improved by sharing the supernet's weights during the candidate architectures' evaluation. This strategy could greatly speed up the search process but suffer a challenge that the evaluation based on sharing weights is not predictive enough. Recently, pruning the supernet during the search has been proven to be an efficient way to alleviate this problem. However, the pruning direction in complex-structured search space remains unexplored. In this paper, we revisited the role of path dropout strategy, which drops the neural operations instead of the neurons, in supernet training, and several interesting characters of the supernet trained with dropout are found. Based on the observations, a Hierarchically-Ordered Pruning Neural Architecture Search (HOPNAS) algorithm is proposed by dynamically pruning the supernet with a proper pruning direction. Experimental results indicate that our method is competitive with state-of-the-art approaches on CIFAR10 and ImageNet.

Effective Automatic Method Selection for Nonlinear Regression Modeling

Metalearning, an important part of artificial intelligence, represents a promising approach for the task of automatic selection of appropriate methods or algorithms. This paper is interested in recommending a suitable estimator for nonlinear regression modeling, particularly in recommending either the standard nonlinear least squares estimator or one of such available alternative estimators, which is highly robust with respect to the presence of outliers in the data. The authors hold the opinion that theoretical considerations will never be able to formulate such recommendations for the nonlinear regression context. Instead, metalearning is explored here as an original approach suitable for this task. In this paper, four different approaches for automatic method selection for nonlinear regression are proposed and computations over a training database of 643 real publicly available datasets are performed. Particularly, while the metalearning results may be harmed by the imbalanced number of groups, an effective approach yields much improved results, performing a novel combination of supervised feature selection by random forest and oversampling by synthetic minority oversampling technique (SMOTE). As a by-product, the computations bring arguments in favor of the very recent nonlinear least weighted squares estimator, which turns out to outperform other (and much more renowned) estimators in a quite large percentage of datasets.

Supervised Anomaly Detection with Highly Imbalanced Datasets Using Capsule Networks

Detecting anomalous patterns in data is a relevant task in many practical applications, such as defective items detection in industrial inspection systems, cancer identification in medical images, or attacker detection in network intrusion detection systems. This paper focuses on detection of anomalous images, this is images that visually deviate from a reference set of regular data. While anomaly detection has been widely studied in the context of classical machine learning, the application of modern deep learning techniques in this field is still limited. We here propose a capsule-based network for anomaly detection in an extremely imbalanced fully supervised context: we assume that anomaly samples are available, but their amount is limited if compared to regular data. By using a variant of the standard CapsNet architecture, we achieved state-of-the-art results on the MNIST, F-MNIST and K-MNIST datasets.