arXiv subjects

Qi Wei

Publications and source records attributed to Qi Wei.

At least 37 records · Page 2Linked to original sources

arXiv2025

Nonequilibrium mean-field approach for quantum transport with off-diagonal disorder

For the nanoscale structures, disorder scattering plays a vital role in the carriers' transport, including electrons and high-frequency phonons. The capability for effectively treating the disorders, including both diagonal and off-diagonal disorders, is indispensable for quantum transport simulation of realistic device materials. In this work, we report a self-consistent nonequilibrium mean-field quantum transport approach, by combining the auxiliary coherent potential approximation (ACPA) and non-equilibrium Green's function method, for calculating the phonon transport through disordered material structures with the force-constant disorders (including the Anderson-type disorder). The nonequilibrium vertex correction (NVC) is derived in an extended local degree of freedom to account for both the multiple disorder scattering by force-constant disorder and the nonequilibrium quantum statistics. We have tested ACPA-NVC method with the fluctuation-dissipation theorem at the equilibrium and obtained very good agreement with supercell calculations for the phonon transmission. To demonstrate the applicability, we apply ACPA-NVC to calculate the thermal conductance for the disordered Ni/Pt interface, and important effects of force-constant disorder are revealed. ACPA-NVC method provides an effective quantum transport approach for simulating disordered nanoscale devices, and the generalization to simulate disordered nanoelectronic device is straightforward.

cond-mat.mes-hall↗

arXiv2024

Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data

Fine-tuning vision-language models (VLMs) with abundant unlabeled data recently has attracted increasing attention. Existing methods that resort to the pseudolabeling strategy would suffer from heavily incorrect hard pseudolabels when VLMs exhibit low zero-shot performance in downstream tasks. To alleviate this issue, we propose a Candidate Pseudolabel Learning method, termed CPL, to fine-tune VLMs with suitable candidate pseudolabels of unlabeled data in downstream tasks. The core of our method lies in the generation strategy of candidate pseudolabels, which progressively generates refined candidate pseudolabels by both intra- and inter-instance label selection, based on a confidence score matrix for all unlabeled data. This strategy can result in better performance in true label inclusion and class-balanced instance selection. In this way, we can directly apply existing loss functions to learn with generated candidate psueudolabels. Extensive experiments on nine benchmark datasets with three learning paradigms demonstrate the effectiveness of our method. Our code can be found at https://github.com/vanillaer/CPL-ICML2024.

cs.LG↗

arXiv2024

Empirical Studies of Propagation Characteristics and Modeling Based on XL-MIMO Channel Measurement: From Far-Field to Near-Field

In the sixth-generation (6G), the extremely large-scale multiple-input-multiple-output (XL-MIMO) is considered a promising enabling technology. With the further expansion of array element number and frequency bands, near-field effects will be more likely to occur in 6G communication systems. The near-field radio communications (NFRC) will become crucial in 6G communication systems. It is known that the channel research is very important for the development and performance evaluation of the communication systems. In this paper, we will systematically investigate the channel measurements and modeling for the emerging NFRC. First, the principle design of massive MIMO channel measurement platform are solved. Second, an indoor XL-MIMO channel measurement campaign with 1600 array elements is conducted, and the channel characteristics are extracted and validated in the near-field region. Then, the outdoor XL-MIMO channel measurement campaign with 320 array elements is conducted, and the channel characteristics are extracted and modeled from near-field to far-field (NF-FF) region. The spatial non-stationary characteristics of angular spread at the transmitting end are more important in modeling. We hope that this work will give some reference to the near-field and far-field research for 6G.

cs.IT↗

arXiv2024

Analysis of Near-Field Effects, Spatial Non-Stationary Characteristics Based on 11-15 GHz Channel Measurement in Indoor Scenario

In the sixth-generation (6G), with the further expansion of array element number and frequency bands, the wireless communications are expected to operate in the near-field region. The near-field radio communications (NFRC) will become crucial in 6G communication systems. The new mid-band (6-24 GHz) is the 6G potential candidate spectrum. In this paper, we will investigate the channel measurements and characteristics for the emerging NFRC. First, the near-field spherical-wave signal model is derived in detail, and the stationary interval (SI) division method is discussed based on the channel statistical properties. Then, the influence of line-of-sight (LOS) and obstructed-LOS (OLOS) environments on the near-field effects and spatial non-stationary (SnS) characteristic are explored based on the near-field channel measurements at 11-15 GHz band. We hope that this work will give some reference to the NFRC research.

eess.SP↗

arXiv2023

Improving Generalization in Meta-Learning via Meta-Gradient Augmentation

Meta-learning methods typically follow a two-loop framework, where each loop potentially suffers from notorious overfitting, hindering rapid adaptation and generalization to new tasks. Existing schemes solve it by enhancing the mutual-exclusivity or diversity of training samples, but these data manipulation strategies are data-dependent and insufficiently flexible. This work alleviates overfitting in meta-learning from the perspective of gradient regularization and proposes a data-independent \textbf{M}eta-\textbf{G}radient \textbf{Aug}mentation (\textbf{MGAug}) method. The key idea is to first break the rote memories by network pruning to address memorization overfitting in the inner loop, and then the gradients of pruned sub-networks naturally form the high-quality augmentation of the meta-gradient to alleviate learner overfitting in the outer loop. Specifically, we explore three pruning strategies, including \textit{random width pruning}, \textit{random parameter pruning}, and a newly proposed \textit{catfish pruning} that measures a Meta-Memorization Carrying Amount (MMCA) score for each parameter and prunes high-score ones to break rote memories as much as possible. The proposed MGAug is theoretically guaranteed by the generalization bound from the PAC-Bayes framework. In addition, we extend a lightweight version, called MGAug-MaxUp, as a trade-off between performance gains and resource overhead. Extensive experiments on multiple few-shot learning benchmarks validate MGAug's effectiveness and significant improvement over various meta-baselines. The code is publicly available at \url{https://github.com/xxLifeLover/Meta-Gradient-Augmentation}.

cs.LG↗

arXiv2023

Ionization Induced by the Ponderomotive Force in Intense and High-Frequency Laser Fields

Atomic stabilization is a universal phenomenon that occurs when atoms interact with intense and high-frequency laser fields. In this work, we systematically study the influence of the ponderomotive (PM) force, present around the laser focus, on atomic stabilization. We show that the PM force could induce tunneling and even over-barrier ionization to the otherwise stabilized atoms. Such effect may overweight the typical multiphoton ionization under moderate laser intensities. Our work highlights the importance of an improved treatment of atomic stabilization that includes the influence of the PM force.

physics.atom-ph↗

arXiv2023

Fine-Grained Classification with Noisy Labels

Learning with noisy labels (LNL) aims to ensure model generalization given a label-corrupted training set. In this work, we investigate a rarely studied scenario of LNL on fine-grained datasets (LNL-FG), which is more practical and challenging as large inter-class ambiguities among fine-grained classes cause more noisy labels. We empirically show that existing methods that work well for LNL fail to achieve satisfying performance for LNL-FG, arising the practical need of effective solutions for LNL-FG. To this end, we propose a novel framework called stochastic noise-tolerated supervised contrastive learning (SNSCL) that confronts label noise by encouraging distinguishable representation. Specifically, we design a noise-tolerated supervised contrastive learning loss that incorporates a weight-aware mechanism for noisy label correction and selectively updating momentum queue lists. By this mechanism, we mitigate the effects of noisy anchors and avoid inserting noisy labels into the momentum-updated queue. Besides, to avoid manually-defined augmentation strategies in contrastive learning, we propose an efficient stochastic module that samples feature embeddings from a generated distribution, which can also enhance the representation ability of deep models. SNSCL is general and compatible with prevailing robust LNL strategies to improve their performance for LNL-FG. Extensive experiments demonstrate the effectiveness of SNSCL.

cs.CV↗

arXiv2022

Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization

Sample selection is an effective strategy to mitigate the effect of label noise in robust learning. Typical strategies commonly apply the small-loss criterion to identify clean samples. However, those samples lying around the decision boundary with large losses usually entangle with noisy examples, which would be discarded with this criterion, leading to the heavy degeneration of the generalization performance. In this paper, we propose a novel selection strategy, \textbf{S}elf-\textbf{F}il\textbf{t}ering (SFT), that utilizes the fluctuation of noisy examples in historical predictions to filter them, which can avoid the selection bias of the small-loss criterion for the boundary examples. Specifically, we introduce a memory bank module that stores the historical predictions of each example and dynamically updates to support the selection for the subsequent learning iteration. Besides, to reduce the accumulated error of the sample selection bias of SFT, we devise a regularization term to penalize the confident output distribution. By increasing the weight of the misclassified categories with this term, the loss function is robust to label noise in mild conditions. We conduct extensive experiments on three benchmarks with variant noise types and achieve the new state-of-the-art. Ablation studies and further analysis verify the virtue of SFT for sample selection in robust learning.

cs.CV↗

arXiv2022

Imputing Missing Observations with Time Sliced Synthetic Minority Oversampling Technique

We present a simple yet novel time series imputation technique with the goal of constructing an irregular time series that is uniform across every sample in a data set. Specifically, we fix a grid defined by the midpoints of non-overlapping bins (dubbed "slices") of observation times and ensure that each sample has values for all of the features at that given time. This allows one to both impute fully missing observations to allow uniform time series classification across the entire data and, in special cases, to impute individually missing features. To do so, we slightly generalize the well-known class imbalance algorithm SMOTE \cite{smote} to allow component wise nearest neighbor interpolation that preserves correlations when there are no missing features. We visualize the method in the simplified setting of 2-dimensional uncoupled harmonic oscillators. Next, we use tSMOTE to train an Encoder/Decoder long-short term memory (LSTM) model with Logistic Regression for predicting and classifying distinct trajectories of different 2D oscillators. After illustrating the the utility of tSMOTE in this context, we use the same architecture to train a clinical model for COVID-19 disease severity on an imputed data set. Our experiments show an improvement over standard mean and median imputation techniques by allowing a wider class of patient trajectories to be recognized by the model, as well as improvement over aggregated classification models.

cs.LG↗

arXiv2021

Realization of Heisenberg models of spin systems with polar molecules in pendular states

We show that ultracold polar diatomic or linear molecules, oriented in an external electric field and mutually coupled by dipole-dipole interactions, can be used to realize the exact Heisenberg XYZ, XXZ and XY models without invoking any approximation. The two lowest lying excited pendular states coupled by microwave or radio-frequency fields are used to encode the pseudo-spin. We map out the general features of the models by evaluating the models' constants as functions of the molecular dipole moment, rotational constant, strength and direction of the external field as well as the distance between molecules. We calculate the phase diagram for a linear chain of polar molecules based on the Heisenberg models and discuss their drawbacks, advantages, and potential applications.

quant-ph↗

arXiv2021

Tailoring Luminescent Properties of SrS:Ce by Modulating Defects: Sr-Deficiency and Na+ Doping

Ce3+ doped SrS phosphors with a charge-compensating Na+ for light-emitting diode (LED) applications have been successfully synthesized via a solid-state reaction method, which can be indexed to rock-salt-like crystal structures of Fm-3m space group. SrS:(Ce3+)x(x=0.005-0.05) and SrS:(Ce3+)0.01,(Na+)y(y=0.005-0.030) phosphors were excited by 430nm UV-VIS light, associated to the 5d1-4f1 transition of Ce3+. The composition-optimized SrS:(Ce3+)0.01,(Na+)0.015 phosphors showed an intense broad emission band at 430-700nm. The doping of Na+ was probed by solid-state nuclear magnetic resonance. The 430 nm pumped with white LED (w-LED) combining SrS:(Ce3+)0.01,(Na+)0.015 phosphors and Sr2Si5N8:Eu2+ phosphors shows a color-rendering index (Ra) of 89.7. The proposed strategy provides new avenues for design and realization of novel high color quality solid-state lighting emitting diodes (SS-LEDS).

cond-mat.mtrl-sci↗

arXiv2021

Learning to Rectify for Robust Learning with Noisy Labels

Label noise significantly degrades the generalization ability of deep models in applications. Effective strategies and approaches, \textit{e.g.} re-weighting, or loss correction, are designed to alleviate the negative impact of label noise when training a neural network. Those existing works usually rely on the pre-specified architecture and manually tuning the additional hyper-parameters. In this paper, we propose warped probabilistic inference (WarPI) to achieve adaptively rectifying the training procedure for the classification network within the meta-learning scenario. In contrast to the deterministic models, WarPI is formulated as a hierarchical probabilistic model by learning an amortization meta-network, which can resolve sample ambiguity and be therefore more robust to serious label noise. Unlike the existing approximated weighting function of directly generating weight values from losses, our meta-network is learned to estimate a rectifying vector from the input of the logits and labels, which has the capability of leveraging sufficient information lying in them. This provides an effective way to rectify the learning procedure for the classification network, demonstrating a significant improvement of the generalization ability. Besides, modeling the rectifying vector as a latent variable and learning the meta-network can be seamlessly integrated into the SGD optimization of the classification network. We evaluate WarPI on four benchmarks of robust learning with noisy labels and achieve the new state-of-the-art under variant noise types. Extensive study and analysis also demonstrate the effectiveness of our model.

cs.LG↗

arXiv2021

RaP-Net: A Region-wise and Point-wise Weighting Network to Extract Robust Features for Indoor Localization

Feature extraction plays an important role in visual localization. Unreliable features on dynamic objects or repetitive regions will interfere with feature matching and challenge indoor localization greatly. To address the problem, we propose a novel network, RaP-Net, to simultaneously predict region-wise invariability and point-wise reliability, and then extract features by considering both of them. We also introduce a new dataset, named OpenLORIS-Location, to train the proposed network. The dataset contains 1553 images from 93 indoor locations. Various appearance changes between images of the same location are included and can help the model to learn the invariability in typical indoor scenes. Experimental results show that the proposed RaP-Net trained with OpenLORIS-Location dataset achieves excellent performance in the feature matching task and significantly outperforms state-of-the-arts feature algorithms in indoor localization. The RaP-Net code and dataset are available at https://github.com/ivipsourcecode/RaP-Net.

cs.CV↗

arXiv2021

Hyperspectral Image Super-Resolution via Deep Prior Regularization with Parameter Estimation

Hyperspectral image (HSI) super-resolution is commonly used to overcome the hardware limitations of existing hyperspectral imaging systems on spatial resolution. It fuses a low-resolution (LR) HSI and a high-resolution (HR) conventional image of the same scene to obtain an HR HSI. In this work, we propose a method that integrates a physical model and deep prior information. Specifically, a novel, yet effective two-stream fusion network is designed to serve as a {regularizer} for the fusion problem. This fusion problem is formulated as an optimization problem whose solution can be obtained by solving a Sylvester equation. Furthermore, the regularization parameter is simultaneously estimated to automatically adjust contribution of the physical model and {the} learned prior to reconstruct the final HR HSI. Experimental results on {both simulated and real data} demonstrate the superiority of the proposed method over other state-of-the-art methods on both quantitative and qualitative comparisons.

eess.IV↗

arXiv2020

DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features

A robust and efficient Simultaneous Localization and Mapping (SLAM) system is essential for robot autonomy. For visual SLAM algorithms, though the theoretical framework has been well established for most aspects, feature extraction and association is still empirically designed in most cases, and can be vulnerable in complex environments. This paper shows that feature extraction with deep convolutional neural networks (CNNs) can be seamlessly incorporated into a modern SLAM framework. The proposed SLAM system utilizes a state-of-the-art CNN to detect keypoints in each image frame, and to give not only keypoint descriptors, but also a global descriptor of the whole image. These local and global features are then used by different SLAM modules, resulting in much more robustness against environmental changes and viewpoint changes compared with using hand-crafted features. We also train a visual vocabulary of local features with a Bag of Words (BoW) method. Based on the local features, global features, and the vocabulary, a highly reliable loop closure detection method is built. Experimental results show that all the proposed modules significantly outperforms the baseline, and the full system achieves much lower trajectory errors and much higher correct rates on all evaluated data. Furthermore, by optimizing the CNN with Intel OpenVINO toolkit and utilizing the Fast BoW library, the system benefits greatly from the SIMD (single-instruction-multiple-data) techniques in modern CPUs. The full system can run in real-time without any GPU or other accelerators. The code is public at https://github.com/ivipsourcecode/dxslam.

cs.CV↗

arXiv2019

Elastic higher-order topological insulators with quantization of the quadrupole moments

We demonstrate that HOTIs with the quantization of the quadrupole moments can be realized in the two-dimensional elastic phononic crystals (PnCs). Both one-dimensional (1D) topological edge states and zero-dimensional (0D) topological corner states are visualized and can be transformed each other by tuning the crystalline symmetry in a hierarchical structure. The systematic band structure calculations indicate that elastic wave energy in the hierarchical structure can be localized with remarkable robustness, which is very promising for new generations of integrated solid-state phononic circuits with a great versatility.

physics.app-ph↗

arXiv2019

LMVP: Video Predictor with Leaked Motion Information

We propose a Leaked Motion Video Predictor (LMVP) to predict future frames by capturing the spatial and temporal dependencies from given inputs. The motion is modeled by a newly proposed component, motion guider, which plays the role of both learner and teacher. Specifically, it {\em learns} the temporal features from real data and {\em guides} the generator to predict future frames. The spatial consistency in video is modeled by an adaptive filtering network. To further ensure the spatio-temporal consistency of the prediction, a discriminator is also adopted to distinguish the real and generated frames. Further, the discriminator leaks information to the motion guider and the generator to help the learning of motion. The proposed LMVP can effectively learn the static and temporal features in videos without the need for human labeling. Experiments on synthetic and real data demonstrate that LMVP can yield state-of-the-art results.

cs.CV↗

arXiv2018

Hu-Fu: Hardware and Software Collaborative Attack Framework against Neural Networks

Recently, Deep Learning (DL), especially Convolutional Neural Network (CNN), develops rapidly and is applied to many tasks, such as image classification, face recognition, image segmentation, and human detection. Due to its superior performance, DL-based models have a wide range of application in many areas, some of which are extremely safety-critical, e.g. intelligent surveillance and autonomous driving. Due to the latency and privacy problem of cloud computing, embedded accelerators are popular in these safety-critical areas. However, the robustness of the embedded DL system might be harmed by inserting hardware/software Trojans into the accelerator and the neural network model, since the accelerator and deploy tool (or neural network model) are usually provided by third-party companies. Fortunately, inserting hardware Trojans can only achieve inflexible attack, which means that hardware Trojans can easily break down the whole system or exchange two outputs, but can't make CNN recognize unknown pictures as targets. Though inserting software Trojans has more freedom of attack, it often requires tampering input images, which is not easy for attackers. So, in this paper, we propose a hardware-software collaborative attack framework to inject hidden neural network Trojans, which works as a back-door without requiring manipulating input images and is flexible for different scenarios. We test our attack framework for image classification and face recognition tasks, and get attack success rate of 92.6% and 100% on CIFAR10 and YouTube Faces, respectively, while keeping almost the same accuracy as the unattacked model in the normal mode. In addition, we show a specific attack scenario in which a face recognition system is attacked and gives a specific wrong answer.

cs.CR↗