In this paper, the appealing features of a dual-polarized intelligent reflecting surface (IRS) are exploited to improve the performance of dual-polarized massive multiple-input multiple-output (MIMO) with non-orthogonal multiple access (NOMA) under imperfect successive interference cancellation (SIC). By considering the downlink of a multi-cluster scenario, the IRSs assist the base station (BS) to multiplex subsets of users in the polarization domain. Our novel strategy alleviates the impact of imperfect SIC and enables users to exploit polarization diversity with near-zero inter-subset interference. Our results show that when the IRSs are large enough, the proposed scheme always outperforms conventional massive MIMO-NOMA and MIMO-OMA systems even if SIC error propagation is present. It is also confirmed that dual-polarized IRSs can make cross-polar transmissions beneficial to the users, allowing them to improve their performance through polarization diversity.
Ground Penetrating Radar (GPR) is one of the most important non-destructive evaluation (NDE) devices to detect subsurface objects (i.e., rebars, utility pipes) and reveal the underground scene. The two biggest challenges in GPR-based inspection are the GPR data collection and subsurface target imaging. To address these challenges, we propose a robotic solution that automates the GPR data collection process with a free motion pattern. It facilitates the 3D metric GPR imaging by tagging the pose information with GPR measurement in real-time. We also introduce a deep neural network (DNN) based GPR data analysis method which includes a noise removal segmentation module to clear the noise in GPR raw data and a DielectricNet to estimate the dielectric value of subsurface media in each GPR B-scan data. We use both the field and synthetic data to verify the proposed method. Experimental results demonstrate that our proposed method can achieve better performance and faster processing speed in GPR data collection and 3D GPR imaging than other methods.
Ground Penetrating Radar (GPR) is one of the most important non-destructive evaluation (NDE) devices to detect the subsurface objects (i.e. rebars, utility pipes) and reveal the underground scene. Due to the background noise and unknown dielectric property of GPR data, the reconstruction of the subsurface objects with metric information remains the main challenge in GPR inspection. In this letter, a novel metric GPR migration method is proposed consisting of three steps to address the above challenge. Firstly, a noise removal segmentation model is introduced to clear the GPR raw data; furthermore, a DielectricNet is proposed to predict the dielectric of each GPR B-scan data and the depth of a target object; at the last step, we optimize the migration algorithm by using random motion pattern, thus to obtain the 3D metric migration result. We use both the field and synthetic data to verify the proposed method, experimental results show that our proposed method is able to achieve at least 10% improvement in reconstruction accuracy compared with the conventional migration methods.
Ground Penetrating Radar (GPR) is one of the most important non-destructive evaluation (NDE) instruments to detect and locate underground objects (i.e. rebars, utility pipes). Many of the previous researches focus on GPR image-based feature detection only, and none can process sparse GPR measurements to successfully reconstruct a very fine and detailed 3D model of underground objects for better visualization. To address this problem, this paper presents a novel robotic system to collect GPR data, localize the underground utilities, and reconstruct the underground objects' dense point cloud model. This system is composed of three modules: 1) visual-inertial-based GPR data collection module which tags the GPR measurements with positioning information provided by an omnidirectional robot; 2) a deep neural network (DNN) migration module to interpret the raw GPR B-scan image into a cross-section of object model; 3) a DNN-based 3D reconstruction module, i.e., GPRNet, to generate underground utility model with the fine 3D point cloud. The experiments show that our method can generate a dense and complete point cloud model of pipe-shaped utilities based on a sparse input, i.e., GPR raw data, with various levels of incompleteness and noise. The experiment results on synthetic data as well as field test data verified the effectiveness of our method.
Graph Neural Networks (GNNs) have achieved tremendous success in graph representation learning. Unfortunately, current GNNs usually rely on loading the entire attributed graph into the network for processing. This implicit assumption may not be satisfied with limited memory resources, especially when the attributed graph is large. In this paper, we propose a Binary Graph Convolutional Network (Bi-GCN), which binarizes both the network parameters and input node features. Besides, the original matrix multiplications are revised to binary operations for accelerations. According to the theoretical analysis, our Bi-GCN can reduce the memory consumption by ~31x for both the network parameters and input data, and accelerate the inference speed by ~53x. Extensive experiments have demonstrated that our Bi-GCN can give a comparable prediction performance compared to the full-precision baselines. Besides, our binarization approach can be easily applied to other GNNs, which has been verified in the experiments.
The deficiency of 3D segmentation labels is one of the main obstacles to effective point cloud segmentation, especially for scenes in the wild with varieties of different objects. To alleviate this issue, we propose a novel deep graph convolutional network-based framework for large-scale semantic scene segmentation in point clouds with sole 2D supervision. Different with numerous preceding multi-view supervised approaches focusing on single object point clouds, we argue that 2D supervision is capable of providing sufficient guidance information for training 3D semantic segmentation models of natural scene point clouds while not explicitly capturing their inherent structures, even with only single view per training sample. Specifically, a Graph-based Pyramid Feature Network (GPFN) is designed to implicitly infer both global and local features of point sets and an Observability Network (OBSNet) is introduced to further solve object occlusion problem caused by complicated spatial relations of objects in 3D scenes. During the projection process, perspective rendering and semantic fusion modules are proposed to provide refined 2D supervision signals for training along with a 2D-3D joint optimization strategy. Extensive experimental results demonstrate the effectiveness of our 2D supervised framework, which achieves comparable results with the state-of-the-art approaches trained with full 3D labels, for semantic point cloud segmentation on the popular SUNCG synthetic dataset and S3DIS real-world dataset.
In multi-label learning, each instance is associated with multiple labels and the crucial task is how to leverage label correlations in building models. Deep neural network methods usually jointly embed the feature and label information into a latent space to exploit label correlations. However, the success of these methods highly depends on the precise choice of model depth. Deep forest is a recent deep learning framework based on tree model ensembles, which does not rely on backpropagation. We consider the advantages of deep forest models are very appropriate for solving multi-label problems. Therefore we design the Multi-Label Deep Forest (MLDF) method with two mechanisms: measure-aware feature reuse and measure-aware layer growth. The measure-aware feature reuse mechanism reuses the good representation in the previous layer guided by confidence. The measure-aware layer growth mechanism ensures MLDF gradually increase the model complexity by performance measure. MLDF handles two challenging problems at the same time: one is restricting the model complexity to ease the overfitting issue; another is optimizing the performance measure on user's demand since there are many different measures in the multi-label evaluation. Experiments show that our proposal not only beats the compared methods over six measures on benchmark datasets but also enjoys label correlation discovery and other desired properties in multi-label learning.
In this paper, we reformulate the forest representation learning approach as an additive model which boosts the augmented feature instead of the prediction. We substantially improve the upper bound of generalization gap from $\mathcal{O}(\sqrt\frac{\ln m}{m})$ to $\mathcal{O}(\frac{\ln m}{m})$, while $\lambda$ - the margin ratio between the margin standard deviation and the margin mean is small enough. This tighter upper bound inspires us to optimize the margin distribution ratio $\lambda$. Therefore, we design the margin distribution reweighting approach (mdDF) to achieve small ratio $\lambda$ by boosting the augmented feature. Experiments and visualizations confirm the effectiveness of the approach in terms of performance and representation learning ability. This study offers a novel understanding of the cascaded deep forest from the margin-theory perspective and further uses the mdDF approach to guide the layer-by-layer forest representation learning.