Searcharxiv⌕ Search

arXiv subjects

Yang Lu

Publications and source records attributed to Yang Lu.

At least 163 records · Page 9Linked to original sources
arXiv2023

Magnetic Exciton-Polariton with Strongly Coupled Atomic and Photonic Anisotropies

Anisotropy plays a key role in science and engineering. However, the interplay between the material and engineered photonic anisotropies has hardly been explored due to the vastly different length scales. Here we demonstrate a matter-light hybrid system, exciton-polaritons in a 2D antiferromagnet, CrSBr, coupled with an anisotropic photonic crystal (PC) cavity, where the spin, atomic lattice, and photonic lattices anisotropies are strongly correlated, giving rise to unusual properties of the hybrid system and new possibilities of tuning. We show exceptionally strong coupling between engineered anisotropic optical modes and anisotropic excitons in CrSBr, which is stable against excitation densities a few orders of magnitude higher than polaritons in isotropic materials. Moreover, the polaritons feature a highly anisotropic polarization tunable by tens of degrees by controlling the matter-light coupling via, for instance, spatial alignment between the material and photonic lattices, magnetic field, temperature, cavity detuning and cavity quality-factors. The demonstrated system provides a prototype where atomic- and photonic-scale orders strongly couple, opening opportunities of photonic engineering of quantum materials and novel photonic devices, such as compact, on-chip polarized light source and polariton laser.

physics.optics↗
arXiv2023

Fast List Decoding of High-Rate Polar Codes

Due to the ability to provide superior error-correction performance, the successive cancellation list (SCL) algorithm is widely regarded as one of the most promising decoding algorithms for polar codes with short-to-moderate code lengths. However, the application of SCL decoding in low-latency communication scenarios is limited due to its sequential nature. To reduce the decoding latency, developing tailored fast and efficient list decoding algorithms of specific polar substituent codes (special nodes) is a promising solution. Recently, fast list decoding algorithms are proposed by considering special nodes with low code rates. Aiming to further speedup the SCL decoding, this paper presents fast list decoding algorithms for two types of high-rate special nodes, namely single-parity-check (SPC) nodes and sequence rate one or single-parity-check (SR1/SPC) nodes. In particular, we develop two classes of fast list decoding algorithms for these nodes, where the first class uses a sequential decoding procedure to yield decoding latency that is linear with the list size, and the second further parallelizes the decoding process by pre-determining the redundant candidate paths offline. Simulation results show that the proposed list decoding algorithms are able to achieve up to 70.7\% lower decoding latency than state-of-the-art fast SCL decoders, while exhibiting the same error-correction performance.

cs.IT↗
arXiv2023

GNN-Based Beamforming for Sum-Rate Maximization in MU-MISO Networks

The advantages of graph neural networks (GNNs) in leveraging the graph topology of wireless networks have drawn increasing attentions. This paper studies the GNN-based learning approach for the sum-rate maximization in multiple-user multiple-input single-output (MU-MISO) networks subject to the users' individual data rate requirements and the power budget of the base station. By modeling the MU-MISO network as a graph, a GNN-based architecture named CRGAT is proposed to directly map the channel state information to the beamforming vectors. The attention-enabled aggregation and the residual-assisted combination are adopted to enhance the learning capability and avoid the oversmoothing issue. Furthermore, a novel activation function is proposed for the constraint due to the limited power budget at the base station. The CRGAT is trained in an unsupervised learning manner with two proposed loss functions. An evaluation method is proposed for the learning-based approach, based on which the effectiveness of the proposed CRGAT is validated in comparison with several convex optimization and learning based approaches. Numerical results are provided to reveal the advantages of the CRGAT including the millisecond-level response with limited optimality performance loss, the scalability to different number of users and power budgets, and the adaptability to different system settings.

eess.SY↗
arXiv2023

Decision Fusion Network with Perception Fine-tuning for Defect Classification

Surface defect inspection is an important task in industrial inspection. Deep learning-based methods have demonstrated promising performance in this domain. Nevertheless, these methods still suffer from misjudgment when encountering challenges such as low-contrast defects and complex backgrounds. To overcome these issues, we present a decision fusion network (DFNet) that incorporates the semantic decision with the feature decision to strengthen the decision ability of the network. In particular, we introduce a decision fusion module (DFM) that extracts a semantic vector from the semantic decision branch and a feature vector for the feature decision branch and fuses them to make the final classification decision. In addition, we propose a perception fine-tuning module (PFM) that fine-tunes the foreground and background during the segmentation stage. PFM generates the semantic and feature outputs that are sent to the classification decision stage. Furthermore, we present an inner-outer separation weight matrix to address the impact of label edge uncertainty during segmentation supervision. Our experimental results on the publicly available datasets including KolektorSDD2 (96.1% AP) and Magnetic-tile-defect-datasets (94.6% mAP) demonstrate the effectiveness of the proposed method.

cs.CV↗
arXiv2023

CINFormer: Transformer network with multi-stage CNN feature injection for surface defect segmentation

Surface defect inspection is of great importance for industrial manufacture and production. Though defect inspection methods based on deep learning have made significant progress, there are still some challenges for these methods, such as indistinguishable weak defects and defect-like interference in the background. To address these issues, we propose a transformer network with multi-stage CNN (Convolutional Neural Network) feature injection for surface defect segmentation, which is a UNet-like structure named CINFormer. CINFormer presents a simple yet effective feature integration mechanism that injects the multi-level CNN features of the input image into different stages of the transformer network in the encoder. This can maintain the merit of CNN capturing detailed features and that of transformer depressing noises in the background, which facilitates accurate defect detection. In addition, CINFormer presents a Top-K self-attention module to focus on tokens with more important information about the defects, so as to further reduce the impact of the redundant background. Extensive experiments conducted on the surface defect datasets DAGM 2007, Magnetic tile, and NEU show that the proposed CINFormer achieves state-of-the-art performance in defect detection.

cs.CV↗
arXiv2023

Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects

Surface defect inspection is a very challenging task in which surface defects usually show weak appearances or exist under complex backgrounds. Most high-accuracy defect detection methods require expensive computation and storage overhead, making them less practical in some resource-constrained defect detection applications. Although some lightweight methods have achieved real-time inference speed with fewer parameters, they show poor detection accuracy in complex defect scenarios. To this end, we develop a Global Context Aggregation Network (GCANet) for lightweight saliency detection of surface defects on the encoder-decoder structure. First, we introduce a novel transformer encoder on the top layer of the lightweight backbone, which captures global context information through a novel Depth-wise Self-Attention (DSA) module. The proposed DSA performs element-wise similarity in channel dimension while maintaining linear complexity. In addition, we introduce a novel Channel Reference Attention (CRA) module before each decoder block to strengthen the representation of multi-level features in the bottom-up path. The proposed CRA exploits the channel correlation between features at different layers to adaptively enhance feature representation. The experimental results on three public defect datasets demonstrate that the proposed network achieves a better trade-off between accuracy and running efficiency compared with other 17 state-of-the-art methods. Specifically, GCANet achieves competitive accuracy (91.79% $F_β^{w}$, 93.55% $S_α$, and 97.35% $E_ϕ$) on SD-saliency-900 while running 272fps on a single gpu.

cs.CV↗
arXiv2023

A Classification of Observation-Driven State-Space Count Models for Panel Data

State-space models are widely used in many applications. In the domain of count data, one such example is the model proposed by Harvey and Fernandes (1989). Unlike many of its parameter-driven alternatives, this model is observation-driven, leading to closed-form expressions for the predictive density. In this paper, we demonstrate the need to extend the model of Harvey and Fernandes (1989) by showing that their model is not variance stationary. Our extension can accommodate for a wide range of variance processes that are either increasing, decreasing, or stationary, while keeping the tractability of the original model. Simulation and numerical studies are included to illustrate the performance of our method.

stat.ME↗
arXiv2023

Label-Noise Learning with Intrinsically Long-Tailed Data

Label noise is one of the key factors that lead to the poor generalization of deep learning models. Existing label-noise learning methods usually assume that the ground-truth classes of the training data are balanced. However, the real-world data is often imbalanced, leading to the inconsistency between observed and intrinsic class distribution with label noises. In this case, it is hard to distinguish clean samples from noisy samples on the intrinsic tail classes with the unknown intrinsic class distribution. In this paper, we propose a learning framework for label-noise learning with intrinsically long-tailed data. Specifically, we propose two-stage bi-dimensional sample selection (TABASCO) to better separate clean samples from noisy samples, especially for the tail classes. TABASCO consists of two new separation metrics that complement each other to compensate for the limitation of using a single metric in sample separation. Extensive experiments on benchmarks demonstrate the effectiveness of our method. Our code is available at https://github.com/Wakings/TABASCO.

cs.LG↗
arXiv2023

Learning-based Near-optimal Motion Planning for Intelligent Vehicles with Uncertain Dynamics

Motion planning has been an important research topic in achieving safe and flexible maneuvers for intelligent vehicles. However, it remains challenging to realize efficient and optimal planning in the presence of uncertain model dynamics. In this paper, a sparse kernel-based reinforcement learning (RL) algorithm with Gaussian Process (GP) Regression (called GP-SKRL) is proposed to achieve online adaption and near-optimal motion planning performance. In this algorithm, we design an efficient sparse GP regression method to learn the uncertain dynamics. Based on the updated model, a sparse kernel-based policy iteration algorithm with an exponential barrier function is designed to learn the near-optimal planning policies with the capability to avoid dynamic obstacles. Thereby, batch-mode GP-SKRL with online adaption capability can estimate the changing system dynamics. The converged RL policies are then deployed on vehicles efficiently under a safety-aware module. As a result, the produced driving actions are safe and less conservative, and the planning performance has been noticeably improved. Extensive simulation results show that GP-SKRL outperforms several advanced motion planning methods in terms of average cumulative cost, trajectory length, and task completion time. In particular, experiments on a Hongqi E-HS3 vehicle demonstrate that superior GP-SKRL provides a practical planning solution.

cs.RO↗
arXiv2023

Communication-Sensing Region for Cell-Free Massive MIMO ISAC Systems

This paper investigates the system model and the transmit beamforming design for the Cell-Free massive multi-input multi-output (MIMO) integrated sensing and communication (ISAC) system. The impact of the uncertainty of the target locations on the propagation of wireless signals is considered during both uplink and downlink phases, and especially, the main statistics of the MIMO channel estimation error are theoretically derived in the closed-form fashion. A fundamental performance metric, termed communication-sensing (C-S) region, is defined for the considered system via three cases, i.e., the sensing-only case, the communication-only case and the ISAC case. The transmit beamforming design problems for the three cases are respectively carried out through different reformulations, e.g., the Lagrangian dual transform and the quadratic fractional transform, and some combinations of the block coordinate descent method and the successive convex approximation method. Numerical results present a 3-dimensional C-S region with a dynamic number of access points to illustrate the trade-off between communication and radar sensing. The advantage for radar sensing of the Cell-Free massive MIMO system is also studied via a comparison with the traditional cellular system. Finally, the efficacy of the proposed beamforming scheme is validated in comparison with zero-forcing and maximum ratio transmission schemes.

cs.IT↗
arXiv2023

Cross Chain Bribery Contracts: Majority vs Mighty Minority

Bribery is a perilous issue in the real world, especially in an economical aspect. This fraudulence is unavoidable, and more importantly, it is more difficult to trace in case smart contracts are utilized for bribing on a distributed public blockchain. In our paper, we propose a new threat to the security of a blockchain system, cross-chain bribery using smart contracts. An arbitrary wealthy briber can utilize cross-chain smart contracts to manipulate a consensus mechanism on a victim's blockchain or to disgrace a victim's blockchain. To better understand this threat, our paper proposes a framework to analyze bribery using cross-chain smart contracts. We analyze the amount of incentive to bribe rational miners in a victim's blockchain and also a full cost of conducting a cross-chain bribery attack. The result is that such attacks can be carried out with a reasonable amount of money or cryptocurrencies.

cs.CR↗
arXiv2023

Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment

Long-tailed data is still a big challenge for deep neural networks, even though they have achieved great success on balanced data. We observe that vanilla training on long-tailed data with cross-entropy loss makes the instance-rich head classes severely squeeze the spatial distribution of the tail classes, which leads to difficulty in classifying tail class samples. Furthermore, the original cross-entropy loss can only propagate gradient short-lively because the gradient in softmax form rapidly approaches zero as the logit difference increases. This phenomenon is called softmax saturation. It is unfavorable for training on balanced data, but can be utilized to adjust the validity of the samples in long-tailed data, thereby solving the distorted embedding space of long-tailed problems. To this end, this paper proposes the Gaussian clouded logit adjustment by Gaussian perturbation of different class logits with varied amplitude. We define the amplitude of perturbation as cloud size and set relatively large cloud sizes to tail classes. The large cloud size can reduce the softmax saturation and thereby making tail class samples more active as well as enlarging the embedding space. To alleviate the bias in a classifier, we therefore propose the class-based effective number sampling strategy with classifier re-training. Extensive experiments on benchmark datasets validate the superior performance of the proposed method. Source code is available at https://github.com/Keke921/GCLLoss.

cs.CV↗
arXiv2023

PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition

Pedestrian attribute recognition (PAR) has received increasing attention because of its wide application in video surveillance and pedestrian analysis. Extracting robust feature representation is one of the key challenges in this task. The existing methods mainly use the convolutional neural network (CNN) as the backbone network to extract features. However, these methods mainly focus on small discriminative regions while ignoring the global perspective. To overcome these limitations, we propose a pure transformer-based multi-task PAR network named PARFormer, which includes four modules. In the feature extraction module, we build a transformer-based strong baseline for feature extraction, which achieves competitive results on several PAR benchmarks compared with the existing CNN-based baseline methods. In the feature processing module, we propose an effective data augmentation strategy named batch random mask (BRM) block to reinforce the attentive feature learning of random patches. Furthermore, we propose a multi-attribute center loss (MACL) to enhance the inter-attribute discriminability in the feature representations. In the viewpoint perception module, we explore the impact of viewpoints on pedestrian attributes, and propose a multi-view contrastive loss (MCVL) that enables the network to exploit the viewpoint information. In the attribute recognition module, we alleviate the negative-positive imbalance problem to generate the attribute predictions. The above modules interact and jointly learn a highly discriminative feature space, and supervise the generation of the final features. Extensive experimental results show that the proposed PARFormer network performs well compared to the state-of-the-art methods on several public datasets, including PETA, RAP, and PA100K. Code will be released at https://github.com/xwf199/PARFormer.

cs.CV↗
arXiv2023

Integrated motion control and energy management of series hybrid electric vehicles: A multi-objective MPC approach

This paper considers the integrated motion control and energy management problems of the series hybrid electric vehicles (SHEV) with constraints. We propose a multi-objective model predictive control (MOMPC)-based energy management approach, which is embedded with the motion control to guarantee driving comfort. In addition, due to the slow response of the engine, it may cause excessive batter power when HEVs work in different conditions (e.g., uphill or sudden acceleration) with a certain request power; this implies the discharge current is too large. A battery current constraint is designed and incorporated into the MOMPC optimization problem and hence avoids the extra high charge-discharge current. This prevents potential safety hazards and extends the battery's life. Finally, numerical experiments are performed to verify the proposed approach.

math.OC↗
arXiv2023

Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation

Deep neural networks have made huge progress in the last few decades. However, as the real-world data often exhibits a long-tailed distribution, vanilla deep models tend to be heavily biased toward the majority classes. To address this problem, state-of-the-art methods usually adopt a mixture of experts (MoE) to focus on different parts of the long-tailed distribution. Experts in these methods are with the same model depth, which neglects the fact that different classes may have different preferences to be fit by models with different depths. To this end, we propose a novel MoE-based method called Self-Heterogeneous Integration with Knowledge Excavation (SHIKE). We first propose Depth-wise Knowledge Fusion (DKF) to fuse features between different shallow parts and the deep part in one network for each expert, which makes experts more diverse in terms of representation. Based on DKF, we further propose Dynamic Knowledge Transfer (DKT) to reduce the influence of the hardest negative class that has a non-negligible impact on the tail classes in our MoE framework. As a result, the classification accuracy of long-tailed data can be significantly improved, especially for the tail classes. SHIKE achieves the state-of-the-art performance of 56.3%, 60.3%, 75.4%, and 41.9% on CIFAR100-LT (IF100), ImageNet-LT, iNaturalist 2018, and Places-LT, respectively.

cs.CV↗
arXiv2023

Personalized Federated Learning on Long-Tailed Data via Adversarial Feature Augmentation

Personalized Federated Learning (PFL) aims to learn personalized models for each client based on the knowledge across all clients in a privacy-preserving manner. Existing PFL methods generally assume that the underlying global data across all clients are uniformly distributed without considering the long-tail distribution. The joint problem of data heterogeneity and long-tail distribution in the FL environment is more challenging and severely affects the performance of personalized models. In this paper, we propose a PFL method called Federated Learning with Adversarial Feature Augmentation (FedAFA) to address this joint problem in PFL. FedAFA optimizes the personalized model for each client by producing a balanced feature set to enhance the local minority classes. The local minority class features are generated by transferring the knowledge from the local majority class features extracted by the global model in an adversarial example learning manner. The experimental results on benchmarks under different settings of data heterogeneity and long-tail distribution demonstrate that FedAFA significantly improves the personalized performance of each client compared with the state-of-the-art PFL algorithm. The code is available at https://github.com/pxqian/FedAFA.

cs.LG↗
arXiv2023

VPU-EM: An Event-based Modeling Framework to Evaluate NPU Performance and Power Efficiency at Scale

State-of-art NPUs are typically architected as a self-contained sub-system with multiple heterogeneous hardware computing modules, and a dataflow-driven programming model. There lacks well-established methodology and tools in the industry to evaluate and compare the performance of NPUs from different architectures. We present an event-based performance modeling framework, VPU-EM, targeting scalable performance evaluation of modern NPUs across diversified AI workloads. The framework adopts high-level event-based system-simulation methodology to abstract away design details for speed, while maintaining hardware pipelining, concurrency and interaction with software task scheduling. It is natively developed in Python and built to interface directly with AI frameworks such as Tensorflow, PyTorch, ONNX and OpenVINO, linking various in-house NPU graph compilers to achieve optimized full model performance. Furthermore, VPU-EM also provides the capability to model power characteristics of NPU in Power-EM mode to enable joint performance/power analysis. Using VPU-EM, we conduct performance/power analysis of models from representative neural network architecture. We demonstrate that even though this framework is developed for Intel VPU, an Intel in-house NPU IP technology, the methodology can be generalized for analysis of modern NPUs.

cs.AR↗
arXiv2023

Federated Semi-Supervised Learning with Annotation Heterogeneity

Federated Semi-Supervised Learning (FSSL) aims to learn a global model from different clients in an environment with both labeled and unlabeled data. Most of the existing FSSL work generally assumes that both types of data are available on each client. In this paper, we study a more general problem setup of FSSL with annotation heterogeneity, where each client can hold an arbitrary percentage (0%-100%) of labeled data. To this end, we propose a novel FSSL framework called Heterogeneously Annotated Semi-Supervised LEarning (HASSLE). Specifically, it is a dual-model framework with two models trained separately on labeled and unlabeled data such that it can be simply applied to a client with an arbitrary labeling percentage. Furthermore, a mutual learning strategy called Supervised-Unsupervised Mutual Alignment (SUMA) is proposed for the dual models within HASSLE with global residual alignment and model proximity alignment. Subsequently, the dual models can implicitly learn from both types of data across different clients, although each dual model is only trained locally on a single type of data. Experiments verify that the dual models in HASSLE learned by SUMA can mutually learn from each other, thereby effectively utilizing the information of both types of data across different clients.

cs.LG↗