Searcharxiv⌕ Search

arXiv subjects

Lingfeng Zhang

Publications and source records attributed to Lingfeng Zhang.

68 records · Page 4Linked to original sources

Spiking Wavelet Transformer

Spiking neural networks (SNNs) offer an energy-efficient alternative to conventional deep learning by emulating the event-driven processing manner of the brain. Incorporating Transformers with SNNs has shown promise for accuracy. However, they struggle to learn high-frequency patterns, such as moving edges and pixel-level brightness changes, because they rely on the global self-attention mechanism. Learning these high-frequency representations is challenging but essential for SNN-based event-driven vision. To address this issue, we propose the Spiking Wavelet Transformer (SWformer), an attention-free architecture that effectively learns comprehensive spatial-frequency features in a spike-driven manner by leveraging the sparse wavelet transform. The critical component is a Frequency-Aware Token Mixer (FATM) with three branches: 1) spiking wavelet learner for spatial-frequency domain learning, 2) convolution-based learner for spatial feature extraction, and 3) spiking pointwise convolution for cross-channel information aggregation - with negative spike dynamics incorporated in 1) to enhance frequency representation. The FATM enables the SWformer to outperform vanilla Spiking Transformers in capturing high-frequency visual components, as evidenced by our empirical results. Experiments on both static and neuromorphic datasets demonstrate SWformer's effectiveness in capturing spatial-frequency patterns in a multiplication-free and event-driven fashion, outperforming state-of-the-art SNNs. SWformer achieves a 22.03% reduction in parameter count, and a 2.52% performance improvement on the ImageNet dataset compared to vanilla Spiking Transformers. The code is available at: https://github.com/bic-L/Spiking-Wavelet-Transformer.

cs.NE↗

RRAM-Based Bio-Inspired Circuits for Mobile Epileptic Correlation Extraction and Seizure Prediction

Non-invasive mobile electroencephalography (EEG) acquisition systems have been utilized for long-term monitoring of seizures, yet they suffer from limited battery life. Resistive random access memory (RRAM) is widely used in computing-in-memory(CIM) systems, which offers an ideal platform for reducing the computational energy consumption of seizure prediction algorithms, potentially solving the endurance issues of mobile EEG systems. To address this challenge, inspired by neuronal mechanisms, we propose a RRAM-based bio-inspired circuit system for correlation feature extraction and seizure prediction. This system achieves a high average sensitivity of 91.2% and a low false positive rate per hour (FPR/h) of 0.11 on the CHB-MIT seizure dataset. The chip under simulation demonstrates an area of approximately 0.83 mm2 and a latency of 62.2 μs. Power consumption is recorded at 24.4 mW during the feature extraction phase and 19.01 mW in the seizure prediction phase, with a cumulative energy consumption of 1.515 μJ for a 3-second window data processing, predicting 29.2 minutes ahead. This method exhibits an 81.3% reduction in computational energy relative to the most efficient existing seizure prediction approaches, establishing a new benchmark for energy efficiency.

eess.SP↗

Orbital origin of magnetic moment enhancement induced by charge density wave in kagome FeGe

Interactions among various electronic states such as CDW, magnetism, and superconductivity are of high significance in strongly correlated systems. While significant progress has been made in understanding the relationship between CDW and superconductivity, the interplay between CDW and magnetic order remains largely elusive. Kagome lattices, which intertwine nontrivial topology, charge order, and magnetism, offer an ideal platform for such studies. The kagome magnet FeGe, hosting the unique coupling between CDW and magnetism, has recently garnered considerable attention in that respect. Here we reveal the significant role of the orbital coupling effect during the CDW phase transition, highlighting the orbital origin of the magnetic moment enhancement in FeGe. Our X ray absorption experiments and first principles calculations illuminate the temperature dependent behavior of Fe3d_Ge4p orbital hybridization and corroborate its pivotal impact on the magnetic properties of FeGe. These findings introduce an orbital dimension to the correlation between charge and magnetic degrees of freedom, advancing our understanding of the intriguing quantum phases resulting from this interplay.

cond-mat.str-el↗

1-D CNN-Based Online Signature Verification with Federated Learning

Online signature verification plays a pivotal role in security infrastructures. However, conventional online signature verification models pose significant risks to data privacy, especially during training processes. To mitigate these concerns, we propose a novel federated learning framework that leverages 1-D Convolutional Neural Networks (CNN) for online signature verification. Furthermore, our experiments demonstrate the effectiveness of our framework regarding 1-D CNN and federated learning. Particularly, the experiment results highlight that our framework 1) minimizes local computational resources; 2) enhances transfer effects with substantial initialization data; 3) presents remarkable scalability. The centralized 1-D CNN model achieves an Equal Error Rate (EER) of 3.33% and an accuracy of 96.25%. Meanwhile, configurations with 2, 5, and 10 agents yield EERs of 5.42%, 5.83%, and 5.63%, along with accuracies of 95.21%, 94.17%, and 94.06%, respectively.

cs.CR↗

Realization of a Two-Dimensional Lieb Lattice in a Metal-Inorganic Framework with Flat Bands and Topological Edge States

Flat bands and Dirac cones in materials are at the source of the exotic electronic and topological properties. The Lieb lattice is expected to host these electronic structures, arising from quantum destructive interference. Nevertheless, the experimental realization of a two-dimensional Lieb lattice remained challenging to date due to its intrinsic structural instability. After computationally designing a Platinum-Phosphorus (Pt-P) Lieb lattice, we have successfully overcome its structural instability and synthesized it on a gold substrate via molecular beam epitaxy. Low-temperature scanning tunneling microscopy and spectroscopy verified the Lieb lattice's morphology and electronic flat bands. Furthermore, topological Dirac edge states stemming from pronounced spin-orbit coupling induced by heavy Pt atoms have been predicted. These findings convincingly open perspectives for creating metal-inorganic framework-based atomic lattices, offering prospects for strongly correlated phases interplayed with topology.

physics.app-ph↗

TriHelper: Zero-Shot Object Navigation with Dynamic Assistance

Navigating toward specific objects in unknown environments without additional training, known as Zero-Shot object navigation, poses a significant challenge in the field of robotics, which demands high levels of auxiliary information and strategic planning. Traditional works have focused on holistic solutions, overlooking the specific challenges agents encounter during navigation such as collision, low exploration efficiency, and misidentification of targets. To address these challenges, our work proposes TriHelper, a novel framework designed to assist agents dynamically through three primary navigation challenges: collision, exploration, and detection. Specifically, our framework consists of three innovative components: (i) Collision Helper, (ii) Exploration Helper, and (iii) Detection Helper. These components work collaboratively to solve these challenges throughout the navigation process. Experiments on the Habitat-Matterport 3D (HM3D) and Gibson datasets demonstrate that TriHelper significantly outperforms all existing baseline methods in Zero-Shot object navigation, showcasing superior success rates and exploration efficiency. Our ablation studies further underscore the effectiveness of each helper in addressing their respective challenges, notably enhancing the agent's navigation capabilities. By proposing TriHelper, we offer a fresh perspective on advancing the object navigation task, paving the way for future research in the domain of Embodied AI and visual-based navigation.

cs.RO↗

On A Parabolic Equation in MEMS with An External Pressure

The parabolic problem $u_t-Δu=\frac{λf(x)}{(1-u)^2}+P$ on a bounded domain $Ω$ of $R^n$ with Dirichlet boundary condition models the microelectromechanical systems(MEMS) device with an external pressure term. In this paper, we classify the behavior of the solution to this equation. We first show that under certain initial conditions, there exists critical constants $P^*$ and $λ_P^*$ such that when $0\leq P\leq P^*$, $0<λ\leq λ_P^*$, there exists a global solution, while for $0\leq P\leq P^*,λ>λ_P^*$ or $P>P^*$, the solution quenches in finite time. The estimate of voltage $λ_P^*$, quenching time $T$ and pressure term $P^*$ are investigated. The quenching set $Σ$ is proved to be a compact subset of $Ω$ with an additional condition, provided $Ω\subset R^n$ is a convex bounded set. In particular, if $Ω$ is radially symmetric, then the origin is the only quenching point. Furthermore, we not only derive the two-side bound estimate for the quenching solution, but also study the asymptotic behavior of the quenching solution in finite time.

math.AP↗

Orbital hybridization-driven charge density wave transition in CsV3Sb5 kagome superconductor

Owing to its inherent non-trivial geometry, the unique structural motif of the recently discovered Kagome topological superconductor AV3Sb5 is an ideal host of diverse topologically non-trivial phenomena, including giant anomalous Hall conductivity, topological charge order, charge density wave, and unconventional superconductivity. Despite possessing a normal-state CDW order in the form of topological chiral charge order and diverse superconducting gaps structures, it remains unclear how fundamental atomic-level properties and many-body effects including Fermi surface nesting, electron-phonon coupling, and orbital hybridization contribute to these symmetry-breaking phenomena. Here, we report the direct participation of the V3d-Sb5p orbital hybridization in mediating the CDW phase transition in CsV3Sb5. The combination of temperature-dependent X-ray absorption and first principles studies clearly indicate the Inverse Star of David structure as the preferred reconstruction in the low-temperature CDW phase. Our results highlight the critical role that Sb orbitals plays and establish orbital hybridization as the direct mediator of the CDW states and structural transition dynamics in Kagome unconventional superconductors. This is a significant step towards the fundamental understanding and control of the emerging correlated phases from the Kagome lattice through the orbital interactions and provide promising approaches to novel regimes in unconventional orders and topology.

cond-mat.supr-con↗

A Novel Center-based Deep Contrastive Metric Learning Method for the Detection of Polymicrogyria in Pediatric Brain MRI

Polymicrogyria (PMG) is a disorder of cortical organization mainly seen in children, which can be associated with seizures, developmental delay and motor weakness. PMG is typically diagnosed on magnetic resonance imaging (MRI) but some cases can be challenging to detect even for experienced radiologists. In this study, we create an open pediatric MRI dataset (PPMR) with PMG and controls from the Children's Hospital of Eastern Ontario (CHEO), Ottawa, Canada. The differences between PMG MRIs and control MRIs are subtle and the true distribution of the features of the disease is unknown. This makes automatic detection of cases of potential PMG in MRI difficult. We propose an anomaly detection method based on a novel center-based deep contrastive metric learning loss function (cDCM) which enables the automatic detection of cases of potential PMG. Additionally, based on our proposed loss function, we customize a deep learning model structure that integrates dilated convolution, squeeze-and-excitation blocks and feature fusion for our PPMR dataset. Despite working with a small and imbalanced dataset our method achieves 92.01% recall at 55.04% precision. This will facilitate a computer aided tool for radiologists to select potential PMG MRIs. To the best of our knowledge, this research is the first to apply machine learning techniques to identify PMG from MRI only.

cs.CV↗

Fully Associative Patch-based 1-to-N Matcher for Face Recognition

This paper focuses on improving face recognition performance by a patch-based 1-to-N signature matcher that learns correlations between different facial patches. A Fully Associative Patch-based Signature Matcher (FAPSM) is proposed so that the local matching identity of each patch contributes to the global matching identities of all the patches. The proposed matcher consists of three steps. First, based on the signature, the local matching identity and the corresponding matching score of each patch are computed. Then, a fully associative weight matrix is learned to obtain the global matching identities and scores of all the patches. At last, the l1-regularized weighting is applied to combine the global matching identity of each patch and obtain a final matching identity. The proposed matcher has been integrated with the UR2D system for evaluation. The experimental results indicate that the proposed matcher achieves better performance than the current UR2D system. The Rank-1 accuracy is improved significantly by 3% and 0.55% on the UHDB31 dataset and the IJB-A dataset, respectively.

cs.CV↗

A Hierarchical Matcher using Local Classifier Chains

This paper focuses on improving the performance of current convolutional neural networks in visual recognition without changing the network architecture. A hierarchical matcher is proposed that builds chains of local binary neural networks after one global neural network over all the class labels, named as Local Classifier Chains based Convolutional Neural Network (LCC-CNN). The signature of each sample as two components: global component based on the global network; local component based on local binary networks. The local networks are built based on label pairs created by a similarity matrix and confusion matrix. During matching, each sample travels through one global network and a chain of local networks to obtain its final matching to avoid error propagation. The proposed matcher has been evaluated with image recognition, character recognition and face recognition datasets. The experimental results indicate that the proposed matcher achieves better performance when compared with methods using only a global deep network. Compared with the UR2D system, the accuracy is improved significantly by 1% and 0.17% on the UHDB31 dataset and the IJB-A dataset, respectively.

cs.CV↗

Patch-based Face Recognition using a Hierarchical Multi-label Matcher

This paper proposes a hierarchical multi-label matcher for patch-based face recognition. In signature generation, a face image is iteratively divided into multi-level patches. Two different types of patch divisions and signatures are introduced for 2D facial image and texture-lifted image, respectively. The matcher training consists of three steps. First, local classifiers are built to learn the local matching of each patch. Second, the hierarchical relationships defined between local patches are used to learn the global matching of each patch. Three ways are introduced to learn the global matching: majority voting, l1-regularized weighting, and decision rule. Last, the global matchings of different levels are combined as the final matching. Experimental results on different face recognition tasks demonstrate the effectiveness of the proposed matcher at the cost of gallery generalization. Compared with the UR2D system, the proposed matcher improves the Rank-1 accuracy significantly by 3% and 0.18% on the UHDB31 dataset and IJB-A dataset, respectively.

cs.CV↗

A Face Recognition Signature Combining Patch-based Features with Soft Facial Attributes

This paper focuses on improving face recognition performance with a new signature combining implicit facial features with explicit soft facial attributes. This signature has two components: the existing patch-based features and the soft facial attributes. A deep convolutional neural network adapted from state-of-the-art networks is used to learn the soft facial attributes. Then, a signature matcher is introduced that merges the contributions of both patch-based features and the facial attributes. In this matcher, the matching scores computed from patch-based features and the facial attributes are combined to obtain a final matching score. The matcher is also extended so that different weights are assigned to different facial attributes. The proposed signature and matcher have been evaluated with the UR2D system on the UHDB31 and IJB-A datasets. The experimental results indicate that the proposed signature achieve better performance than using only patch-based features. The Rank-1 accuracy is improved significantly by 4% and 0.37% on the two datasets when compared with the UR2D system.

cs.CV↗

Unsupervised Cross-Domain Recognition by Identifying Compact Joint Subspaces

This paper introduces a new method to solve the cross-domain recognition problem. Different from the traditional domain adaption methods which rely on a global domain shift for all classes between source and target domain, the proposed method is more flexible to capture individual class variations across domains. By adopting a natural and widely used assumption -- "the data samples from the same class should lay on a low-dimensional subspace, even if they come from different domains", the proposed method circumvents the limitation of the global domain shift, and solves the cross-domain recognition by finding the compact joint subspaces of source and target domain. Specifically, given labeled samples in source domain, we construct subspaces for each of the classes. Then we construct subspaces in the target domain, called anchor subspaces, by collecting unlabeled samples that are close to each other and highly likely all fall into the same class. The corresponding class label is then assigned by minimizing a cost function which reflects the overlap and topological structure consistency between subspaces across source and target domains, and within anchor subspaces, respectively.We further combine the anchor subspaces to corresponding source subspaces to construct the compact joint subspaces. Subsequently, one-vs-rest SVM classifiers are trained in the compact joint subspaces and applied to unlabeled data in the target domain. We evaluate the proposed method on two widely used datasets: object recognition dataset for computer vision tasks, and sentiment classification dataset for natural language processing tasks. Comparison results demonstrate that the proposed method outperforms the comparison methods on both datasets.

cs.CV↗