N-Omniglot: a Large-scale Dataset for Spatio-Temporal Sparse Few-shot Learning

Few-shot learning (learning with a few samples) is one of the most important capacities of the human brain. However, the current artificial intelligence systems meet difficulties in achieving this ability, so as the biologically plausible spiking neural networks (SNNs). Datasets for traditional few-shot learning domains provide few amounts of temporal information. And the absence of the neuromorphic datasets has hindered the development of few-shot learning for SNNs. Here, we provide the first neuromorphic dataset: N-Omniglot, using the Dynamic Vision Sensor (DVS). It contains 1623 categories of handwritten characters, with only 20 samples per class. N-Omniglot eliminates the need for a neuromorphic dataset for SNNs with high spareness and tremendous temporal coherence. Additionally, the dataset provides a powerful challenge and a suitable benchmark for developing SNNs algorithm in the few-shot learning domain due to the chronological information of strokes. We also provide the improved nearest neighbor, convolutional network, SiameseNet, and meta-learning algorithm in spiking version for verification.

Heterogeneous Transformer: A Scale Adaptable Neural Network Architecture for Device Activity Detection

To support the modern machine-type communications, a crucial task during the random access phase is device activity detection, which is to detect the active devices from a large number of potential devices based on the received signal at the access point. By utilizing the statistical properties of the channel, state-of-the-art covariance based methods have been demonstrated to achieve better activity detection performance than compressed sensing based methods. However, covariance based methods require to solve a high dimensional nonconvex optimization problem by updating the estimate of the activity status of each device sequentially. Since the number of updates is proportional to the device number, the computational complexity and delay make the iterative updates difficult for real-time implementation especially when the device number scales up. Inspired by the success of deep learning for real-time inference, this paper proposes a learning based method with a customized heterogeneous transformer architecture for device activity detection. By adopting an attention mechanism in the architecture design, the proposed method is able to extract the relevance between device pilots and received signal, is permutation equivariant with respect to devices, and is scale adaptable to different numbers of devices. Simulation results demonstrate that the proposed method achieves better activity detection performance with much shorter computation time than state-of-the-art covariance approach, and generalizes well to different numbers of devices, BS-antennas, and different signal-to-noise ratios.

Learning to Model the Relationship Between Brain Structural and Functional Connectomes

Recent advances in neuroimaging along with algorithmic innovations in statistical learning from network data offer a unique pathway to integrate brain structure and function, and thus facilitate revealing some of the brain's organizing principles at the system level. In this direction, we develop a supervised graph representation learning framework to model the relationship between brain structural connectivity (SC) and functional connectivity (FC) via a graph encoder-decoder system, where the SC is used as input to predict empirical FC. A trainable graph convolutional encoder captures direct and indirect interactions between brain regions-of-interest that mimic actual neural communications, as well as to integrate information from both the structural network topology and nodal (i.e., region-specific) attributes. The encoder learns node-level SC embeddings which are combined to generate (whole brain) graph-level representations for reconstructing empirical FC networks. The proposed end-to-end model utilizes a multi-objective loss function to jointly reconstruct FC networks and learn discriminative graph representations of the SC-to-FC mapping for downstream subject (i.e., graph-level) classification. Comprehensive experiments demonstrate that the learnt representations of said relationship capture valuable information from the intrinsic properties of the subject's brain networks and lead to improved accuracy in classifying a large population of heavy drinkers and non-drinkers from the Human Connectome Project. Our work offers new insights on the relationship between brain networks that support the promising prospect of using graph representation learning to discover more about human brain activity and function.

Progressive Graph Convolution Network for EEG Emotion Recognition

Studies in the area of neuroscience have revealed the relationship between emotional patterns and brain functional regions, demonstrating that dynamic relationships between different brain regions are an essential factor affecting emotion recognition determined through electroencephalography (EEG). Moreover, in EEG emotion recognition, we can observe that clearer boundaries exist between coarse-grained emotions than those between fine-grained emotions, based on the same EEG data; this indicates the concurrence of large coarse- and small fine-grained emotion variations. Thus, the progressive classification process from coarse- to fine-grained categories may be helpful for EEG emotion recognition. Consequently, in this study, we propose a progressive graph convolution network (PGCN) for capturing this inherent characteristic in EEG emotional signals and progressively learning the discriminative EEG features. To fit different EEG patterns, we constructed a dual-graph module to characterize the intrinsic relationship between different EEG channels, containing the dynamic functional connections and static spatial proximity information of brain regions from neuroscience research. Moreover, motivated by the observation of the relationship between coarse- and fine-grained emotions, we adopt a dual-head module that enables the PGCN to progressively learn more discriminative EEG features, from coarse-grained (easy) to fine-grained categories (difficult), referring to the hierarchical characteristic of emotion. To verify the performance of our model, extensive experiments were conducted on two public datasets: SEED-IV and multi-modal physiological emotion database (MPED).

Automated assessment of disease severity of COVID-19 using artificial intelligence with synthetic chest CT

Background: Triage of patients is important to control the pandemic of coronavirus disease 2019 (COVID-19), especially during the peak of the pandemic when clinical resources become extremely limited. Purpose: To develop a method that automatically segments and quantifies lung and pneumonia lesions with synthetic chest CT and assess disease severity in COVID-19 patients. Materials and Methods: In this study, we incorporated data augmentation to generate synthetic chest CT images using public available datasets (285 datasets from "Lung Nodule Analysis 2016"). The synthetic images and masks were used to train a 2D U-net neural network and tested on 203 COVID-19 datasets to generate lung and lesion segmentations. Disease severity scores (DL: damage load; DS: damage score) were calculated based on the segmentations. Correlations between DL/DS and clinical lab tests were evaluated using Pearson's method. A p-value < 0.05 was considered as statistical significant. Results: Automatic lung and lesion segmentations were compared with manual annotations. For lung segmentation, the median values of dice similarity coefficient, Jaccard index and average surface distance, were 98.56%, 97.15% and 0.49 mm, respectively. The same metrics for lesion segmentation were 76.95%, 62.54% and 2.36 mm, respectively. Significant (p << 0.05) correlations were found between DL/DS and percentage lymphocytes tests, with r-values of -0.561 and -0.501, respectively. Conclusion: An AI system that based on thoracic radiographic and data augmentation was proposed to segment lung and lesions in COVID-19 patients. Correlations between imaging findings and clinical lab tests suggested the value of this system as a potential tool to assess disease severity of COVID-19.

VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modeling

User interface modeling is inherently multimodal, which involves several distinct types of data: images, structures and language. The tasks are also diverse, including object detection, language generation and grounding. In this paper, we present VUT, a Versatile UI Transformer that takes multimodal input and simultaneously accomplishes 5 distinct tasks with the same model. Our model consists of a multimodal Transformer encoder that jointly encodes UI images and structures, and performs UI object detection when the UI structures are absent in the input. Our model also consists of an auto-regressive Transformer model that encodes the language input and decodes output, for both question-answering and command grounding with respect to the UI. Our experiments show that for most of the tasks, when trained jointly for multi-tasks, VUT substantially reduces the number of models and footprints needed for performing multiple tasks, while achieving accuracy exceeding or on par with baseline models trained for each individual task.

A Deep-Learning Intelligent System Incorporating Data Augmentation for Short-Term Voltage Stability Assessment of Power Systems

Facing the difficulty of expensive and trivial data collection and annotation, how to make a deep learning-based short-term voltage stability assessment (STVSA) model work well on a small training dataset is a challenging and urgent problem. Although a big enough dataset can be directly generated by contingency simulation, this data generation process is usually cumbersome and inefficient; while data augmentation provides a low-cost and efficient way to artificially inflate the representative and diversified training datasets with label preserving transformations. In this respect, this paper proposes a novel deep-learning intelligent system incorporating data augmentation for STVSA of power systems. First, due to the unavailability of reliable quantitative criteria to judge the stability status for a specific power system, semi-supervised cluster learning is leveraged to obtain labeled samples in an original small dataset. Second, to make deep learning applicable to the small dataset, conditional least squares generative adversarial networks (LSGAN)-based data augmentation is introduced to expand the original dataset via artificially creating additional valid samples. Third, to extract temporal dependencies from the post-disturbance dynamic trajectories of a system, a bi-directional gated recurrent unit with attention mechanism based assessment model is established, which bi-directionally learns the significant time dependencies and automatically allocates attention weights. The test results demonstrate the presented approach manages to achieve better accuracy and a faster response time with original small datasets. Besides classification accuracy, this work employs statistical measures to comprehensively examine the performance of the proposal.

Structure-Aware Multi-Hop Graph Convolution for Graph Neural Networks

In this paper, we propose a spatial graph convolution (GC) to classify signals on a graph. Existing GC methods are limited to using the structural information in the feature space. Additionally, the single step of GCs only uses features on the one-hop neighboring nodes from the target node. In this paper, we propose two methods to improve the performance of GCs: 1) Utilizing structural information in the feature space, and 2) exploiting the multi-hop information in one GC step. In the first method, we define three structural features in the feature space: feature angle, feature distance, and relational embedding. The second method aggregates the node-wise features of multi-hop neighbors in a GC. Both methods can be simultaneously used. We also propose graph neural networks (GNNs) integrating the proposed GC for classifying nodes in 3D point clouds and citation networks. In experiments, the proposed GNNs exhibited a higher classification accuracy than existing methods.

Lepard: Learning partial point cloud matching in rigid and deformable scenes

We present Lepard, a Learning based approach for partial point cloud matching for rigid and deformable scenes. The key characteristic of Lepard is the following approaches that exploit 3D positional knowledge for point cloud matching: 1) An architecture that disentangles point cloud representation into feature space and 3D position space. 2) A position encoding method that explicitly reveals 3D relative distance information through the dot product of vectors. 3) A repositioning technique that modifies the cross-point-cloud relative positions. Ablation studies demonstrate the effectiveness of the above techniques. For rigid point cloud matching, Lepard sets a new state-of-the-art on the 3DMatch / 3DLoMatch benchmarks with 93.6% / 69.0% registration recall. In deformable cases, Lepard achieves +27.1% / +34.8% higher non-rigid feature matching recall than the prior art on our newly constructed 4DMatch / 4DLoMatch benchmark.

Unsupervised COVID-19 Lesion Segmentation in CT Using Cycle Consistent Generative Adversarial Network

COVID-19 has become a global pandemic and is still posing a severe health risk to the public. Accurate and efficient segmentation of pneumonia lesions in CT scans is vital for treatment decision-making. We proposed a novel unsupervised approach using cycle consistent generative adversarial network (cycle-GAN) which automates and accelerates the process of lesion delineation. The workflow includes lung volume segmentation, "synthetic" healthy lung generation, infected and healthy image subtraction, and binary lesion mask creation. The lung volume volume was firstly delineated using a pre-trained U-net and worked as the input for the later network. The cycle-GAN was developed to generate synthetic "healthy" lung CT images from infected lung images. After that, the pneumonia lesions are extracted by subtracting the synthetic "healthy" lung CT images from the "infected" lung CT images. A median filter and K-means clustering were then applied to contour the lesions. The auto segmentation approach was validated on two public datasets (Coronacases and Radiopedia). The Dice coefficients reached 0.748 and 0.730, respectively, for the Coronacases and Radiopedia datasets. Meanwhile, the precision and sensitivity for lesion segmentationdetection are 0.813 and 0.735 for the Coronacases dataset, and 0.773 and 0.726 for the Radiopedia dataset. The performance is comparable to existing supervised segmentation networks and outperforms previous unsupervised ones. The proposed unsupervised segmentation method achieved high accuracy and efficiency in automatic COVID-19 lesion delineation. The segmentation result can serve as a baseline for further manual modification and a quality assurance tool for lesion diagnosis. Furthermore, due to its unsupervised nature, the result is not influenced by physicians' experience which otherwise is crucial for supervised methods.