arXiv subjects

Wei Bao

Publications and source records attributed to Wei Bao.

At least 37 records · Page 2Linked to original sources

arXiv2023

Handling Heavy Occlusion in Dense Crowd Tracking by Focusing on the Heads

With the rapid development of deep learning, object detection and tracking play a vital role in today's society. Being able to identify and track all the pedestrians in the dense crowd scene with computer vision approaches is a typical challenge in this field, also known as the Multiple Object Tracking (MOT) challenge. Modern trackers are required to operate on more and more complicated scenes. According to the MOT20 challenge result, the pedestrian is 4 times denser than the MOT17 challenge. Hence, improving the ability to detect and track in extremely crowded scenes is the aim of this work. In light of the occlusion issue with the human body, the heads are usually easier to identify. In this work, we have designed a joint head and body detector in an anchor-free style to boost the detection recall and precision performance of pedestrians in both small and medium sizes. Innovatively, our model does not require information on the statistical head-body ratio for common pedestrians detection for training. Instead, the proposed model learns the ratio dynamically. To verify the effectiveness of the proposed model, we evaluate the model with extensive experiments on different datasets, including MOT20, Crowdhuman, and HT21 datasets. As a result, our proposed method significantly improves both the recall and precision rate on small & medium sized pedestrians and achieves state-of-the-art results in these challenging datasets.

cs.CV↗

arXiv2023

Online Task Assignment with Controllable Processing Time

We study a new online assignment problem, called the Online Task Assignment with Controllable Processing Time. In a bipartite graph, a set of online vertices (tasks) should be assigned to a set of offline vertices (machines) under the known adversarial distribution (KAD) assumption. We are the first to study controllable processing time in this scenario: There are multiple processing levels for each task and higher level brings larger utility but also larger processing delay. A machine can reject an assignment at the cost of a rejection penalty, taken from a pre-determined rejection budget. Different processing levels cause different penalties. We propose the Online Machine and Level Assignment (OMLA) Algorithm to simultaneously assign an offline machine and a processing level to each online task. We prove that OMLA achieves $1/2$-competitive ratio if each machine has unlimited rejection budget and $Δ/(3Δ-1)$-competitive ratio if each machine has an initial rejection budget up to $Δ$. Interestingly, the competitive ratios do not change under different settings on the controllable processing time and we can conclude that OMLA is "insensitive" to the controllable processing time.

cs.DS↗

arXiv2023

FedMAE: Federated Self-Supervised Learning with One-Block Masked Auto-Encoder

Latest federated learning (FL) methods started to focus on how to use unlabeled data in clients for training due to users' privacy concerns, high labeling costs, or lack of expertise. However, current Federated Semi-Supervised/Self-Supervised Learning (FSSL) approaches fail to learn large-scale images because of the limited computing resources of local clients. In this paper, we introduce a new framework FedMAE, which stands for Federated Masked AutoEncoder, to address the problem of how to utilize unlabeled large-scale images for FL. Specifically, FedMAE can pre-train one-block Masked AutoEncoder (MAE) using large images in lightweight client devices, and then cascades multiple pre-trained one-block MAEs in the server to build a multi-block ViT backbone for downstream tasks. Theoretical analysis and experimental results on image reconstruction and classification show that our FedMAE achieves superior performance compared to the state-of-the-art FSSL methods.

cs.LG↗

arXiv2023

Quasi One-Dimensional Ising-like Antiferromagnetism in the Rare-earth Perovskite Oxide TbScO$_3$

The rare-earth perovskite TbScO$_3$ has been widely used as a substrate for the growth of epitaxial ferroelectric and multiferroic thin films, while its detailed low-temperature magnetic properties were rarely reported. In this paper, we performed detailed magnetization, specific heat and single crystal neutron scattering measurements, along with the crystalline electric field calculations to study the low-temperature magnetic properties of TbScO$_3$. All our results suggest the magnetic Tb$^{3+}$ has an Ising-like pseudo-doublet ground state at low temperatures. Due to the constrain of local point symmetry, these Tb$^{3+}$ Ising moments are confined in the $ab$ plane with a tilt angle of $φ= \pm48^{\mathrm{o}}$ to the $a$ axis. In zero field, the system undergoes an antiferromagnetic phase transition at $T_{\mathrm{N}}=2.53$ K, and forms a $G_xA_y$ noncollinear magnetic structure below $T_{\mathrm{N}}$. We find the dipole-dipole interactions play an important role to determine the magnetic ground state, which are also responsible for the quasi-one-dimensional magnetism in TbScO$_3$. The significant anisotropic diffuse scatterings further confirm the quasi-one-dimensional magnetism along the $c$ axis. The magnetic phase diagram with the field along the easy $b$ axis is well established. In addition to the $G_xA_y$ antiferromagnetic state, there is an exotic field-induced phase emerged near the critical field $B_{\mathrm{c}}\simeq0.7$ T, where three-dimensional magnetic order is suppressed but strong one-dimensional correlations may still exist.

cond-mat.str-el↗

arXiv2023

FedIL: Federated Incremental Learning from Decentralized Unlabeled Data with Convergence Analysis

Most existing federated learning methods assume that clients have fully labeled data to train on, while in reality, it is hard for the clients to get task-specific labels due to users' privacy concerns, high labeling costs, or lack of expertise. This work considers the server with a small labeled dataset and intends to use unlabeled data in multiple clients for semi-supervised learning. We propose a new framework with a generalized model, Federated Incremental Learning (FedIL), to address the problem of how to utilize labeled data in the server and unlabeled data in clients separately in the scenario of Federated Learning (FL). FedIL uses the Iterative Similarity Fusion to enforce the server-client consistency on the predictions of unlabeled data and uses incremental confidence to establish a credible pseudo-label set in each client. We show that FedIL will accelerate model convergence by Cosine Similarity with normalization, proved by Banach Fixed Point Theorem. The code is available at https://anonymous.4open.science/r/fedil.

cs.LG↗

arXiv2023

Random Padding Data Augmentation

The convolutional neural network (CNN) learns the same object in different positions in images, which can improve the recognition accuracy of the model. An implication of this is that CNN may know where the object is. The usefulness of the features' spatial information in CNNs has not been well investigated. In this paper, we found that the model's learning of features' position information hindered the learning of the features' relationship. Therefore, we introduced Random Padding, a new type of padding method for training CNNs that impairs the architecture's capacity to learn position information by adding zero-padding randomly to half of the border of feature maps. Random Padding is parameter-free, simple to construct, and compatible with the majority of CNN-based recognition models. This technique is also complementary to data augmentations such as random cropping, rotation, flipping and erasing, and consistently improves the performance of image classification over strong baselines.

cs.CV↗

arXiv2023

Federated PCA on Grassmann Manifold for Anomaly Detection in IoT Networks

In the era of Internet of Things (IoT), network-wide anomaly detection is a crucial part of monitoring IoT networks due to the inherent security vulnerabilities of most IoT devices. Principal Components Analysis (PCA) has been proposed to separate network traffics into two disjoint subspaces corresponding to normal and malicious behaviors for anomaly detection. However, the privacy concerns and limitations of devices' computing resources compromise the practical effectiveness of PCA. We propose a federated PCA-based Grassmannian optimization framework that coordinates IoT devices to aggregate a joint profile of normal network behaviors for anomaly detection. First, we introduce a privacy-preserving federated PCA framework to simultaneously capture the profile of various IoT devices' traffic. Then, we investigate the alternating direction method of multipliers gradient-based learning on the Grassmann manifold to guarantee fast training and the absence of detecting latency using limited computational resources. Empirical results on the NSL-KDD dataset demonstrate that our method outperforms baseline approaches. Finally, we show that the Grassmann manifold algorithm is highly adapted for IoT anomaly detection, which permits drastically reducing the analysis time of the system. To the best of our knowledge, this is the first federated PCA algorithm for anomaly detection meeting the requirements of IoT networks.

cs.LG↗

arXiv2022

A Comprehensive Evaluation Framework for Deep Model Robustness

Deep neural networks (DNNs) have achieved remarkable performance across a wide range of applications, while they are vulnerable to adversarial examples, which motivates the evaluation and benchmark of model robustness. However, current evaluations usually use simple metrics to study the performance of defenses, which are far from understanding the limitation and weaknesses of these defense methods. Thus, most proposed defenses are quickly shown to be attacked successfully, which results in the ``arm race'' phenomenon between attack and defense. To mitigate this problem, we establish a model robustness evaluation framework containing 23 comprehensive and rigorous metrics, which consider two key perspectives of adversarial learning (i.e., data and model). Through neuron coverage and data imperceptibility, we use data-oriented metrics to measure the integrity of test examples; by delving into model structure and behavior, we exploit model-oriented metrics to further evaluate robustness in the adversarial setting. To fully demonstrate the effectiveness of our framework, we conduct large-scale experiments on multiple datasets including CIFAR-10, SVHN, and ImageNet using different models and defenses with our open-source platform. Overall, our paper provides a comprehensive evaluation framework, where researchers could conduct comprehensive and fast evaluations using the open-source toolkit, and the analytical results could inspire deeper understanding and further improvement to the model robustness.

cs.CV↗

arXiv2022

Hierarchical Federated Learning with Momentum Acceleration in Multi-Tier Networks

In this paper, we propose Hierarchical Federated Learning with Momentum Acceleration (HierMo), a three-tier worker-edge-cloud federated learning algorithm that applies momentum for training acceleration. Momentum is calculated and aggregated in the three tiers. We provide convergence analysis for HierMo, showing a convergence rate of O(1/T). In the analysis, we develop a new approach to characterize model aggregation, momentum aggregation, and their interactions. Based on this result, {we prove that HierMo achieves a tighter convergence upper bound compared with HierFAVG without momentum}. We also propose HierOPT, which optimizes the aggregation periods (worker-edge and edge-cloud aggregation periods) to minimize the loss given a limited training time.

cs.LG↗

arXiv2022

Federated Learning with Nesterov Accelerated Gradient

Federated learning (FL) is a fast-developing technique that allows multiple workers to train a global model based on a distributed dataset. Conventional FL (FedAvg) employs gradient descent algorithm, which may not be efficient enough. Momentum is able to improve the situation by adding an additional momentum step to accelerate the convergence and has demonstrated its benefits in both centralized and FL environments. It is well-known that Nesterov Accelerated Gradient (NAG) is a more advantageous form of momentum, but it is not clear how to quantify the benefits of NAG in FL so far. This motives us to propose FedNAG, which employs NAG in each worker as well as NAG momentum and model aggregation in the aggregator. We provide a detailed convergence analysis of FedNAG and compare it with FedAvg. Extensive experiments based on real-world datasets and trace-driven simulation are conducted, demonstrating that FedNAG increases the learning accuracy by 3-24% and decreases the total training time by 11-70% compared with the benchmarks under a wide range of settings.

cs.LG↗

arXiv2022

Antiferromagnetic structure and magnetic properties of Dy2O2Te: An isostructural analog of the rare-earth superconductors R2O2Bi

The rare-earth compounds R2O2Bi (R=Tb, Dy, Er, Lu, Y) are newly discovered superconductors in the vicinity of a rare-earth magnetic long-range order. In this work, we determine the magnetic order of the parent compound Dy2O2Te by neutron scattering as the A-type antiferromagnetic structure below the Néel temperature TN=9.7K. The large staggered magnetic moment 9.4(1) μB per Dy at T=3.5K lies in the basal ab plane. In a magnetic field, anomalous magnetic properties including the bifurcation between zero-field- and field-cooling magnetization, a butterfly-shaped magnetic hysteresis, and slow magnetic relaxation emerge, which are related to the field-induced metamagnetic transitions in Dy2O2Te. Our experimental findings could stimulate further research on the relation between antiferromagnetism and superconductivity in these rare-earth compounds.

cond-mat.supr-con↗

arXiv2022

Electrically pumped polarized exciton-polaritons in a halide perovskite microcavity

Exciton polaritons, hybrid quasiparticles with part-light part-matter nature in semiconductor microcavities, are extensively investigated for striking phenomena such as polariton condensation and quantum emulation. These phenomena have recently been discovered in emerging lead halide perovskites at elevated temperatures up to room temperature. For advancing these discoveries into practical applications, one critical requirement is the realization of electrically pumped exciton-polaritons. However, electrically pumped polariton light-emitting devices with perovskites have not yet been achieved experimentally. Here, we devise a new method to combine the device with the microcavity and report the first halide perovskite polariton light-emitting device. Specifically, the device is based on a CsPbBr3 capacitive structure, which can inject the electrons and holes from the same electrode, conducive to the formation of excitons and simultaneously maintaining the high quality of the microcavity. In addition, highly polarization-selective polariton emissions have been demonstrated due to the optical birefringence in the CsPbBr3 microplate. This work paves the way for realizing practical polaritonic devices such as high-speed light-emitting devices for information communications and inversionless electrically pumped lasers based on perovskites.

cond-mat.mtrl-sci↗

arXiv2022

DONE: Distributed Approximate Newton-type Method for Federated Edge Learning

There is growing interest in applying distributed machine learning to edge computing, forming federated edge learning. Federated edge learning faces non-i.i.d. and heterogeneous data, and the communication between edge workers, possibly through distant locations and with unstable wireless networks, is more costly than their local computational overhead. In this work, we propose DONE, a distributed approximate Newton-type algorithm with fast convergence rate for communication-efficient federated edge learning. First, with strongly convex and smooth loss functions, DONE approximates the Newton direction in a distributed manner using the classical Richardson iteration on each edge worker. Second, we prove that DONE has linear-quadratic convergence and analyze its communication complexities. Finally, the experimental results with non-i.i.d. and heterogeneous data show that DONE attains a comparable performance to the Newton's method. Notably, DONE requires fewer communication iterations compared to distributed gradient descent and outperforms DANE and FEDL, state-of-the-art approaches, in the case of non-quadratic loss functions.

cs.LG↗

arXiv2021

Fast Multi-label Learning

Embedding approaches have become one of the most pervasive techniques for multi-label classification. However, the training process of embedding methods usually involves a complex quadratic or semidefinite programming problem, or the model may even involve an NP-hard problem. Thus, such methods are prohibitive on large-scale applications. More importantly, much of the literature has already shown that the binary relevance (BR) method is usually good enough for some applications. Unfortunately, BR runs slowly due to its linear dependence on the size of the input data. The goal of this paper is to provide a simple method, yet with provable guarantees, which can achieve competitive performance without a complex training process. To achieve our goal, we provide a simple stochastic sketch strategy for multi-label classification and present theoretical results from both algorithmic and statistical learning perspectives. Our comprehensive empirical studies corroborate our theoretical findings and demonstrate the superiority of the proposed methods.

cs.LG↗

arXiv2021

The QXS-SAROPT Dataset for Deep Learning in SAR-Optical Data Fusion

Deep learning techniques have made an increasing impact on the field of remote sensing. However, deep neural networks based fusion of multimodal data from different remote sensors with heterogenous characteristics has not been fully explored, due to the lack of availability of big amounts of perfectly aligned multi-sensor image data with diverse scenes of high resolutions, especially for synthetic aperture radar (SAR) data and optical imagery. To promote the development of deep learning based SAR-optical fusion approaches, we release the QXS-SAROPT dataset, which contains 20,000 pairs of SAR-optical image patches. We obtain the SAR patches from SAR satellite GaoFen-3 images and the optical patches from Google Earth images. These images cover three port cities: San Diego, Shanghai and Qingdao. Here, we present a detailed introduction of the construction of the dataset, and show its two representative exemplary applications, namely SAR-optical image matching and SAR ship detection boosted by cross-modal information from optical images. As a large open SAR-optical dataset with multiple scenes of a high resolution, we believe QXS-SAROPT will be of potential value for further research in SAR-optical data fusion technology based on deep learning.

eess.IV↗

arXiv2021

Boosting ship detection in SAR images with complementary pretraining techniques

Deep learning methods have made significant progress in ship detection in synthetic aperture radar (SAR) images. The pretraining technique is usually adopted to support deep neural networks-based SAR ship detectors due to the scarce labeled SAR images. However, directly leveraging ImageNet pretraining is hardly to obtain a good ship detector because of different imaging perspective and geometry. In this paper, to resolve the problem of inconsistent imaging perspective between ImageNet and earth observations, we propose an optical ship detector (OSD) pretraining technique, which transfers the characteristics of ships in earth observations to SAR images from a large-scale aerial image dataset. On the other hand, to handle the problem of different imaging geometry between optical and SAR images, we propose an optical-SAR matching (OSM) pretraining technique, which transfers plentiful texture features from optical images to SAR images by common representation learning on the optical-SAR matching task. Finally, observing that the OSD pretraining based SAR ship detector has a better recall on sea area while the OSM pretraining based SAR ship detector can reduce false alarms on land area, we combine the predictions of the two detectors through weighted boxes fusion to further improve detection results. Extensive experiments on four SAR ship detection datasets and two representative CNN-based detection benchmarks are conducted to show the effectiveness and complementarity of the two proposed detectors, and the state-of-the-art performance of the combination of the two detectors. The proposed method won the sixth place of ship detection in SAR images in 2020 Gaofen challenge.

cs.CV↗

arXiv2021

Extreme Suppression of Antiferromagnetic Order and Critical Scaling in a Two-Dimensional Random Quantum Magnet

Sr$_2$CuTeO$_6$ is a square-lattice Néel antiferromagnet with superexchange between first-neighbor $S=1/2$ Cu spins mediated by plaquette centered Te ions. Substituting Te by W, the affected impurity plaquettes have predominantly second-neighbor interactions, thus causing local magnetic frustration. Here we report a study of Sr$_2$CuTe$_{1-x}$W$_x$O$_6$ using neutron diffraction and $μ$SR techniques, showing that the Néel order vanishes already at $x = 0.025 \pm 0.005$. We explain this extreme order suppression using a two-dimensional Heisenberg spin model, demonstrating that a W-type impurity induces a deformation of the order parameter that decays with distance as $1/r^2$ at temperature $T=0$. The associated logarithmic singularity leads to loss of order for any $x>0$. Order for small $x>0$ and $T>0$ is induced by weak interplane couplings. In the nonmagnetic phase of Sr$_2$CuTe$_{1-x}$W$_x$O$_6$, the $μ$SR relaxation rate exhibits quantum critical scaling with a large dynamic exponent, $z \approx 3$, consistent with a random-singlet state.

cond-mat.str-el↗

arXiv2020

Federated Learning over Wireless Networks: Convergence Analysis and Resource Allocation

There is an increasing interest in a fast-growing machine learning technique called Federated Learning, in which the model training is distributed over mobile user equipments (UEs), exploiting UEs' local computation and training data. Despite its advantages in data privacy-preserving, Federated Learning (FL) still has challenges in heterogeneity across UEs' data and physical resources. We first propose a FL algorithm which can handle the heterogeneous UEs' data challenge without further assumptions except strongly convex and smooth loss functions. We provide the convergence rate characterizing the trade-off between local computation rounds of UE to update its local model and global communication rounds to update the FL global model. We then employ the proposed FL algorithm in wireless networks as a resource allocation optimization problem that captures the trade-off between the FL convergence wall clock time and energy consumption of UEs with heterogeneous computing and power resources. Even though the wireless resource allocation problem of FL is non-convex, we exploit this problem's structure to decompose it into three sub-problems and analyze their closed-form solutions as well as insights to problem design. Finally, we illustrate the theoretical analysis for the new algorithm with Tensorflow experiments and extensive numerical results for the wireless resource allocation sub-problems. The experiment results not only verify the theoretical convergence but also show that our proposed algorithm outperforms the vanilla FedAvg algorithm in terms of convergence rate and testing accuracy.

cs.LG↗