arXiv subjects

Li Wang

Publications and source records attributed to Li Wang.

At least 343 records · Page 19Linked to original sources

arXiv2022

Convolutional Embedding Makes Hierarchical Vision Transformer Stronger

Vision Transformers (ViTs) have recently dominated a range of computer vision tasks, yet it suffers from low training data efficiency and inferior local semantic representation capability without appropriate inductive bias. Convolutional neural networks (CNNs) inherently capture regional-aware semantics, inspiring researchers to introduce CNNs back into the architecture of the ViTs to provide desirable inductive bias for ViTs. However, is the locality achieved by the micro-level CNNs embedded in ViTs good enough? In this paper, we investigate the problem by profoundly exploring how the macro architecture of the hybrid CNNs/ViTs enhances the performances of hierarchical ViTs. Particularly, we study the role of token embedding layers, alias convolutional embedding (CE), and systemically reveal how CE injects desirable inductive bias in ViTs. Besides, we apply the optimal CE configuration to 4 recently released state-of-the-art ViTs, effectively boosting the corresponding performances. Finally, a family of efficient hybrid CNNs/ViTs, dubbed CETNets, are released, which may serve as generic vision backbones. Specifically, CETNets achieve 84.9% Top-1 accuracy on ImageNet-1K (training from scratch), 48.6% box mAP on the COCO benchmark, and 51.6% mIoU on the ADE20K, substantially improving the performances of the corresponding state-of-the-art baselines.

cs.CV↗

arXiv2022

Intelligent Amphibious Ground-Aerial Vehicles: State of the Art Technology for Future Transportation

Amphibious ground-aerial vehicles fuse flying and driving modes to enable more flexible air-land mobility and have received growing attention recently. By analyzing the existing amphibious vehicles, we highlight the autonomous fly-driving functionality for the effective uses of amphibious vehicles in complex three-dimensional urban transportation systems. We review and summarize the key enabling technologies for intelligent flying-driving in existing amphibious vehicle designs, identify major technological barriers and propose potential solutions for future research and innovation. This paper aims to serve as a guide for research and development of intelligent amphibious vehicles for urban transportation toward the future.

cs.RO↗

arXiv2022

Determining anomalies in a semilinear elliptic equation by a minimal number of measurements

We are concerned with the inverse boundary problem of determining anomalies associated with a semilinear elliptic equation of the form $-Δu+a(\mathbf x, u)=0$, where $a(\mathbf x, u)$ is a general nonlinear term that belongs to a Hölder class. It is assumed that the inhomogeneity of $f(\mathbf x, u)$ is contained in a bounded domain $D$ in the sense that outside $D$, $a(\mathbf x, u)=λu$ with $λ\in\mathbb{C}$. We establish novel unique identifiability results in several general scenarios of practical interest. These include determining the support of the inclusion (i.e. $D$) independent of its content (i.e. $a(\mathbf{x}, u)$ in $D$) by a single boundary measurement; and determining both $D$ and $a(\mathbf{x}, u)|_D$ by $M$ boundary measurements, where $M\in\mathbb{N}$ signifies the number of unknown coefficients in $a(\mathbf x, u)$. The mathematical argument is based on microlocally characterising the singularities in the solution $u$ induced by the geometric singularities of $D$, and does not rely on any linearisation technique.

math.AP↗

arXiv2022

Evolving community structure in the international pesticide trade networks

The statistical properties including community structure of the international trade networks of all commodities as a whole have been studied extensively. However, the international trade networks of individual commodities often behave differently. Due to the importance of pesticides in agricultural production and food security, we investigate the evolving community structure in the international pesticide trade networks (iPTNs) of five categories from 2007 to 2018. We unveil the community structures in the undirected and directed iPTNs exhibits regional patterns. However, the regional patterns are very different for undirected and directed networks and for different categories of pesticide. Moreover, the community structure is stabler in the directed iPTNs than in the undirected iPTNs. We also extract the intrinsic community blocks for the directed international trade networks of each pesticide category. It is found that the largest intrinsic community block is the stablest that appears in every pesticide category and contains important economies (Belgium, Germany, Spain, France, United Kingdom, Italy, Netherlands, and Portugal) in Europe. Other important and stable intrinsic community blocks are Canada and the United States in North America, Argentina and Brazil in South America, and Australia and New Zealand in Oceania. These findings imply the importance of geographic distance and the complementarity of important adjacent economies in the international trade of pesticides.

physics.soc-ph↗

arXiv2022

Structure-Enhanced Pop Music Generation via Harmony-Aware Learning

Pop music generation has always been an attractive topic for both musicians and scientists for a long time. However, automatically composing pop music with a satisfactory structure is still a challenging issue. In this paper, we propose to leverage harmony-aware learning for structure-enhanced pop music generation. On the one hand, one of the participants of harmony, chord, represents the harmonic set of multiple notes, which is integrated closely with the spatial structure of music, the texture. On the other hand, the other participant of harmony, chord progression, usually accompanies the development of the music, which promotes the temporal structure of music, the form. Moreover, when chords evolve into chord progression, the texture and form can be bridged by the harmony naturally, which contributes to the joint learning of the two structures. Furthermore, we propose the Harmony-Aware Hierarchical Music Transformer (HAT), which can exploit the structure adaptively from the music, and make the musical tokens interact hierarchically to enhance the structure in multi-level musical elements. Experimental results reveal that compared to the existing methods, HAT owns a much better understanding of the structure and it can also improve the quality of generated music, especially in the form and texture.

cs.SD↗

arXiv2022

Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detection

Monocular 3D object detection is an essential perception task for autonomous driving. However, the high reliance on large-scale labeled data make it costly and time-consuming during model optimization. To reduce such over-reliance on human annotations, we propose Mix-Teaching, an effective semi-supervised learning framework applicable to employ both labeled and unlabeled images in training stage. Mix-Teaching first generates pseudo-labels for unlabeled images by self-training. The student model is then trained on the mixed images possessing much more intensive and precise labeling by merging instance-level image patches into empty backgrounds or labeled images. This is the first to break the image-level limitation and put high-quality pseudo labels from multi frames into one image for semi-supervised training. Besides, as a result of the misalignment between confidence score and localization quality, it's hard to discriminate high-quality pseudo-labels from noisy predictions using only confidence-based criterion. To that end, we further introduce an uncertainty-based filter to help select reliable pseudo boxes for the above mixing operation. To the best of our knowledge, this is the first unified SSL framework for monocular 3D object detection. Mix-Teaching consistently improves MonoFlex and GUPNet by significant margins under various labeling ratios on KITTI dataset. For example, our method achieves around +6.34% AP@0.7 improvement against the GUPNet baseline on validation set when using only 10% labeled data. Besides, by leveraging full training set and the additional 48K raw images of KITTI, it can further improve the MonoFlex by +4.65% improvement on AP@0.7 for car detection, reaching 18.54% AP@0.7, which ranks the 1st place among all monocular based methods on KITTI test leaderboard. The code and pretrained models will be released at https://github.com/yanglei18/Mix-Teaching.

cs.CV↗

arXiv2022

Phase effect and symmetry on pair production in spatially inhomogeneous frequency chirping electric fields

Effect of the carrier envelop phase on the electron-positron pair production is studied in spatially inhomogeneous electric field with symmetrical frequency chirping. In high or low original frequency field without chirping as well as one with chirping, we find that the strength of interference effect of the momentum spectrum and the reduced particle number are all changeable periodically with phase, in particular, these periodical changes are more sensitive to the applied parameters in case of low frequency field. At the small spatial scale, the reduced particle number change is over one order magnitude by phase in small chirping. For the reduced particle number, the different optimal phases are obtained at different spatial scales, however, the larger the chirping is applied, the higher the created pair number is got. Interestingly, some different types of symmetries, i.e., the mutual symmetry of mirror/coincidence for two correlated phases and the individual self symmetry for single phase, are unfolded on the momentum spectrum. The physical reason of the mutual symmetry between two correlated phases and also the individual symmetry for two fixed specific phases are examined and discussed analytically in detail. The combined roles by phase and chirping on the periodic and symmetrical behaviors of the momentum spectrum and the reduced particle number are expected to have the potential extension to more fields such as that with multidimensional spatial coordinate.

hep-ph↗

arXiv2022

Wav2vec-S: Semi-Supervised Pre-Training for Low-Resource ASR

Self-supervised pre-training could effectively improve the performance of low-resource automatic speech recognition (ASR). However, existing self-supervised pre-training are task-agnostic, i.e., could be applied to various downstream tasks. Although it enlarges the scope of its application, the capacity of the pre-trained model is not fully utilized for the ASR task, and the learned representations may not be optimal for ASR. In this work, in order to build a better pre-trained model for low-resource ASR, we propose a pre-training approach called wav2vec-S, where we use task-specific semi-supervised pre-training to refine the self-supervised pre-trained model for the ASR task thus more effectively utilize the capacity of the pre-trained model to generate task-specific representations for ASR. Experiments show that compared to wav2vec 2.0, wav2vec-S only requires a marginal increment of pre-training time but could significantly improve ASR performance on in-domain, cross-domain and cross-lingual datasets. Average relative WER reductions are 24.5% and 6.6% for 1h and 10h fine-tuning, respectively. Furthermore, we show that semi-supervised pre-training could close the representation gap between the self-supervised pre-trained model and the corresponding fine-tuned model through canonical correlation analysis.

eess.AS↗

arXiv2022

Solving multiscale steady radiative transfer equation using neural networks with uniform stability

This paper concerns solving the steady radiative transfer equation with diffusive scaling, using the physics informed neural networks (PINNs). The idea of PINNs is to minimize a least-square loss function, that consists of the residual from the governing equation, the mismatch from the boundary conditions, and other physical constraints such as conservation. It is advantageous of being flexible and easy to execute, and brings the potential for high dimensional problems. Nevertheless, due the presence of small scales, the vanilla PINNs can be extremely unstable for solving multiscale steady transfer equations. In this paper, we propose a new formulation of the loss based on the macro-micro decomposition. We prove that, the new loss function is uniformly stable with respect to the small Knudsen number in the sense that the $L^2$-error of the neural network solution is uniformly controlled by the loss. When the boundary condition is an-isotropic, a boundary layer emerges in the diffusion limit and therefore brings an additional difficulty in training the neural network. To resolve this issue, we include a boundary layer corrector that carries over the sharp transition part of the solution and leaves the rest easy to be approximated. The effectiveness of the new methodology is demonstrated in extensive numerical examples.

math.NA↗

arXiv2022

Two-Stage Mesh Deep Learning for Automated Tooth Segmentation and Landmark Localization on 3D Intraoral Scans

Accurately segmenting teeth and identifying the corresponding anatomical landmarks on dental mesh models are essential in computer-aided orthodontic treatment. Manually performing these two tasks is time-consuming, tedious, and, more importantly, highly dependent on orthodontists' experiences due to the abnormality and large-scale variance of patients' teeth. Some machine learning-based methods have been designed and applied in the orthodontic field to automatically segment dental meshes (e.g., intraoral scans). In contrast, the number of studies on tooth landmark localization is still limited. This paper proposes a two-stage framework based on mesh deep learning (called TS-MDL) for joint tooth labeling and landmark identification on raw intraoral scans. Our TS-MDL first adopts an end-to-end \emph{i}MeshSegNet method (i.e., a variant of the existing MeshSegNet with both improved accuracy and efficiency) to label each tooth on the downsampled scan. Guided by the segmentation outputs, our TS-MDL further selects each tooth's region of interest (ROI) on the original mesh to construct a light-weight variant of the pioneering PointNet (i.e., PointNet-Reg) for regressing the corresponding landmark heatmaps. Our TS-MDL was evaluated on a real-clinical dataset, showing promising segmentation and localization performance. Specifically, \emph{i}MeshSegNet in the first stage of TS-MDL reached an averaged Dice similarity coefficient (DSC) at \textcolor[rgb]{0,0,0}{$0.964\pm0.054$}, significantly outperforming the original MeshSegNet. In the second stage, PointNet-Reg achieved a mean absolute error (MAE) of $0.597\pm0.761 \, mm$ in distances between the prediction and ground truth for $66$ landmarks, which is superior compared with other networks for landmark detection. All these results suggest the potential usage of our TS-MDL in orthodontics.

cs.CV↗

arXiv2022

Detecting fake news by enhanced text representation with multi-EDU-structure awareness

Since fake news poses a serious threat to society and individuals, numerous studies have been brought by considering text, propagation and user profiles. Due to the data collection problem, these methods based on propagation and user profiles are less applicable in the early stages. A good alternative method is to detect news based on text as soon as they are released, and a lot of text-based methods were proposed, which usually utilized words, sentences or paragraphs as basic units. But, word is a too fine-grained unit to express coherent information well, sentence or paragraph is too coarse to show specific information. Which granularity is better and how to utilize it to enhance text representation for fake news detection are two key problems. In this paper, we introduce Elementary Discourse Unit (EDU) whose granularity is between word and sentence, and propose a multi-EDU-structure awareness model to improve text representation for fake news detection, namely EDU4FD. For the multi-EDU-structure awareness, we build the sequence-based EDU representations and the graph-based EDU representations. The former is gotten by modeling the coherence between consecutive EDUs with TextCNN that reflect the semantic coherence. For the latter, we first extract rhetorical relations to build the EDU dependency graph, which can show the global narrative logic and help deliver the main idea truthfully. Then a Relation Graph Attention Network (RGAT) is set to get the graph-based EDU representation. Finally, the two EDU representations are incorporated as the enhanced text representation for fake news detection, using a gated recursive unit combined with a global attention mechanism. Experiments on four cross-source fake news datasets show that our model outperforms the state-of-the-art text-based methods.

cs.CL↗

arXiv2022

Transfer Learning-based Channel Estimation in Orthogonal Frequency Division Multiplexing Systems Using Data-nulling Superimposed Pilots

Data-nulling superimposed pilot (DNSP) effectively alleviates the superimposed interference of superimposed training (ST)-based channel estimation (CE) in orthogonal frequency division multiplexing (OFDM) systems, while facing the challenges of the estimation accuracy and computational complexity. By developing the promising solutions of deep learning (DL) in the physical layer of wireless communication, we fuse the DNSP and DL to tackle these challenges in this paper. Nevertheless, due to the changes of wireless scenarios, the model mismatch of DL leads to the performance degradation of CE, and thus faces the issue of network retraining. To address this issue, a lightweight transfer learning (TL) network is further proposed for the DL-based DNSP scheme, and thus structures a TL-based CE in OFDM systems. Specifically, based on the linear receiver, the least squares estimation is first employed to extract the initial features of CE. With the extracted features, we develop a convolutional neural network (CNN) to fuse the solutions of DLbased CE and the CE of DNSP. Finally, a lightweight TL network is constructed to address the model mismatch. To this end, a novel CE network for the DNSP scheme in OFDM systems is structured, which improves its estimation accuracy and alleviates the model mismatch. The experimental results show that in all signal-to-noise-ratio (SNR) regions, the proposed method achieves lower normalized mean squared error (NMSE) than the existing DNSP schemes with minimum mean square error (MMSE)-based CE. For example, when the SNR is 0 decibel (dB), the proposed scheme achieves similar NMSE as that of the MMSE-based CE scheme at 20 dB, thereby significantly improving the estimation accuracy of CE. In addition, relative to the existing schemes, the improvement of the proposed scheme presents its robustness against the impacts of parameter variations.

eess.SP↗

arXiv2022

Representing Brain Anatomical Regularity and Variability by Few-Shot Embedding

Effective representation of brain anatomical architecture is fundamental in understanding brain regularity and variability. Despite numerous efforts, it is still difficult to infer reliable anatomical correspondence at finer scale, given the tremendous individual variability in cortical folding patterns. It is even more challenging to disentangle common and individual patterns when comparing brains at different neuro-developmental stages. In this work, we developed a novel learning-based few-shot embedding framework to encode the cortical folding patterns into a latent space represented by a group of anatomically meaningful embedding vectors. Specifically, we adopted 3-hinge (3HG) network as the substrate and designed an autoencoder-based embedding framework to learn a common embedding vector for each 3HG's multi-hop feature: each 3HG can be represented as a combination of these feature embeddings via a set of individual specific coefficients to characterize individualized anatomical information. That is, the regularity of folding patterns is encoded into the embeddings, while the individual variations are preserved by the multi=hop combination coefficients. To effectively learn the embeddings for the population with very limited samples, few-shot learning was adopted. We applied our method on adult HCP and pediatric datasets with 1,000+ brains (from 34 gestational weeks to young adult). Our experimental results show that: 1) the learned embedding vectors can quantitatively encode the commonality and individuality of cortical folding patterns; 2) with the embeddings we can robustly infer the complicated many-to-many anatomical correspondences among different brains and 3) our model can be successfully transferred to new populations with very limited training samples.

q-bio.NC↗

arXiv2022

Nearly Optimal Stochastic Approximation for Online Principal Subspace Estimation

Principal component analysis (PCA) has been widely used in analyzing high-dimensional data. It converts a set of observed data points of possibly correlated variables into a set of linearly uncorrelated variables via an orthogonal transformation. To handle streaming data and reduce the complexities of PCA, (subspace) online PCA iterations were proposed to iteratively update the orthogonal transformation by taking one observed data point at a time. Existing works on the convergence of (subspace) online PCA iterations mostly focus on the case where sample are almost surely uniformly bounded. In this paper, we analyze the convergence of a subspace online PCA iteration under more practical assumption and obtain a nearly optimal finite-sample error bound. Our convergence rate almost matches the minimax information lower bound. We prove that the convergence is nearly global in the sense that the subspace online PCA iteration is convergent with high probability for random initial guesses. This work also leads to a simpler proof of the recent work on analyzing online PCA for the first principal component only.

math.OC↗

arXiv2022

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-resolve an input image with a magnification factor of $\times$4 based on pairs of low and corresponding high resolution images. The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29.00dB on DIV2K validation set. IMDN is set as the baseline for efficiency measurement. The challenge had 3 tracks including the main track (runtime), sub-track one (model complexity), and sub-track two (overall performance). In the main track, the practical runtime performance of the submissions was evaluated. The rank of the teams were determined directly by the absolute value of the average runtime on the validation set and test set. In sub-track one, the number of parameters and FLOPs were considered. And the individual rankings of the two metrics were summed up to determine a final ranking in this track. In sub-track two, all of the five metrics mentioned in the description of the challenge including runtime, parameter count, FLOPs, activations, and memory consumption were considered. Similar to sub-track one, the rankings of five metrics were summed up to determine a final ranking. The challenge had 303 registered participants, and 43 teams made valid submissions. They gauge the state-of-the-art in efficient single image super-resolution.

cs.CV↗

arXiv2022

Vertically Federated Graph Neural Network for Privacy-Preserving Node Classification

Recently, Graph Neural Network (GNN) has achieved remarkable progresses in various real-world tasks on graph data, consisting of node features and the adjacent information between different nodes. High-performance GNN models always depend on both rich features and complete edge information in graph. However, such information could possibly be isolated by different data holders in practice, which is the so-called data isolation problem. To solve this problem, in this paper, we propose VFGNN, a federated GNN learning paradigm for privacy-preserving node classification task under data vertically partitioned setting, which can be generalized to existing GNN models. Specifically, we split the computation graph into two parts. We leave the private data (i.e., features, edges, and labels) related computations on data holders, and delegate the rest of computations to a semi-honest server. We also propose to apply differential privacy to prevent potential information leakage from the server. We conduct experiments on three benchmarks and the results demonstrate the effectiveness of VFGNN.

cs.LG↗

arXiv2022

Learning Decoupling Features Through Orthogonality Regularization

Keyword spotting (KWS) and speaker verification (SV) are two important tasks in speech applications. Research shows that the state-of-art KWS and SV models are trained independently using different datasets since they expect to learn distinctive acoustic features. However, humans can distinguish language content and the speaker identity simultaneously. Motivated by this, we believe it is important to explore a method that can effectively extract common features while decoupling task-specific features. Bearing this in mind, a two-branch deep network (KWS branch and SV branch) with the same network structure is developed and a novel decoupling feature learning method is proposed to push up the performance of KWS and SV simultaneously where speaker-invariant keyword representations and keyword-invariant speaker representations are expected respectively. Experiments are conducted on Google Speech Commands Dataset (GSCD). The results demonstrate that the orthogonality regularization helps the network to achieve SOTA EER of 1.31% and 1.87% on KWS and SV, respectively.

cs.SD↗

arXiv2022

ImpDet: Exploring Implicit Fields for 3D Object Detection

Conventional 3D object detection approaches concentrate on bounding boxes representation learning with several parameters, i.e., localization, dimension, and orientation. Despite its popularity and universality, such a straightforward paradigm is sensitive to slight numerical deviations, especially in localization. By exploiting the property that point clouds are naturally captured on the surface of objects along with accurate location and intensity information, we introduce a new perspective that views bounding box regression as an implicit function. This leads to our proposed framework, termed Implicit Detection or ImpDet, which leverages implicit field learning for 3D object detection. Our ImpDet assigns specific values to points in different local 3D spaces, thereby high-quality boundaries can be generated by classifying points inside or outside the boundary. To solve the problem of sparsity on the object surface, we further present a simple yet efficient virtual sampling strategy to not only fill the empty region, but also learn rich semantic features to help refine the boundaries. Extensive experimental results on KITTI and Waymo benchmarks demonstrate the effectiveness and robustness of unifying implicit fields into object detection.

cs.CV↗