arXiv subjects

Jian Wang

Publications and source records attributed to Jian Wang.

At least 487 records · Page 27Linked to original sources

arXiv2024

SpaER: Learning Spatio-temporal Equivariant Representations for Fetal Brain Motion Tracking

In this paper, we introduce SpaER, a pioneering method for fetal motion tracking that leverages equivariant filters and self-attention mechanisms to effectively learn spatio-temporal representations. Different from conventional approaches that statically estimate fetal brain motions from pairs of images, our method dynamically tracks the rigid movement patterns of the fetal head across temporal and spatial dimensions. Specifically, we first develop an equivariant neural network that efficiently learns rigid motion sequences through low-dimensional spatial representations of images. Subsequently, we learn spatio-temporal representations by incorporating time encoding and self-attention neural network layers. This approach allows for the capture of long-term dependencies of fetal brain motion and addresses alignment errors due to contrast changes and severe motion artifacts. Our model also provides a geometric deformation estimation that properly addresses image distortions among all time frames. To the best of our knowledge, our approach is the first to learn spatial-temporal representations via deep neural networks for fetal motion tracking without data augmentation. We validated our model using real fetal echo-planar images with simulated and real motions. Our method carries significant potential value in accurately measuring, tracking, and correcting fetal motion in fetal MRI sequences.

eess.IV↗

arXiv2024

Matting by Generation

This paper introduces an innovative approach for image matting that redefines the traditional regression-based task as a generative modeling challenge. Our method harnesses the capabilities of latent diffusion models, enriched with extensive pre-trained knowledge, to regularize the matting process. We present novel architectural innovations that empower our model to produce mattes with superior resolution and detail. The proposed method is versatile and can perform both guidance-free and guidance-based image matting, accommodating a variety of additional cues. Our comprehensive evaluation across three benchmark datasets demonstrates the superior performance of our approach, both quantitatively and qualitatively. The results not only reflect our method's robust effectiveness but also highlight its ability to generate visually compelling mattes that approach photorealistic quality. The project page for this paper is available at https://lightchaserx.github.io/matting-by-generation/

cs.CV↗

arXiv2024

UMono: Physical Model Informed Hybrid CNN-Transformer Framework for Underwater Monocular Depth Estimation

Underwater monocular depth estimation serves as the foundation for tasks such as 3D reconstruction of underwater scenes. However, due to the influence of light and medium, the underwater environment undergoes a distinctive imaging process, which presents challenges in accurately estimating depth from a single image. The existing methods fail to consider the unique characteristics of underwater environments, leading to inadequate estimation results and limited generalization performance. Furthermore, underwater depth estimation requires extracting and fusing both local and global features, which is not fully explored in existing methods. In this paper, an end-to-end learning framework for underwater monocular depth estimation called UMono is presented, which incorporates underwater image formation model characteristics into network architecture, and effectively utilize both local and global features of underwater image. Experimental results demonstrate that the proposed method is effective for underwater monocular depth estimation and outperforms the existing methods in both quantitative and qualitative analyses.

cs.CV↗

arXiv2024

Accelerating Pre-training of Multimodal LLMs via Chain-of-Sight

This paper introduces Chain-of-Sight, a vision-language bridge module that accelerates the pre-training of Multimodal Large Language Models (MLLMs). Our approach employs a sequence of visual resamplers that capture visual details at various spacial scales. This architecture not only leverages global and local visual contexts effectively, but also facilitates the flexible extension of visual tokens through a compound token scaling strategy, allowing up to a 16x increase in the token count post pre-training. Consequently, Chain-of-Sight requires significantly fewer visual tokens in the pre-training phase compared to the fine-tuning phase. This intentional reduction of visual tokens during pre-training notably accelerates the pre-training process, cutting down the wall-clock training time by ~73%. Empirical results on a series of vision-language benchmarks reveal that the pre-train acceleration through Chain-of-Sight is achieved without sacrificing performance, matching or surpassing the standard pipeline of utilizing all visual tokens throughout the entire training process. Further scaling up the number of visual tokens for pre-training leads to stronger performances, competitive to existing approaches in a series of benchmarks.

cs.CV↗

arXiv2024

Dynamical Coulomb Blockade as a Signature of the Sign-Reversing Cooper Pairing Potential

Coulomb blockade occurs for electrons tunneling into nanoislands because of the quantization of charge. Here, using spectroscopy measurements of nonmagnetic islands grown on a high-Tc superconductor [one-unit-cell (1-UC) FeSe], we systematically investigate the dynamical Coulomb blockade (DCB), which is found to reflect the Cooper pairing potential in the superconducting substrate. The tunneling spectra are acquired on single-crystalline Pb nanoislands and show a clear suppression of the tunnel current around zero bias-voltage with a gap-like structure. The observed spectral gaps can be attributed to DCB based on our comprehensive investigations, including experiments with finely varying island sizes and calculations of the spectra using the P(E) theory of DCB. Our detailed analysis suggests that the observed DCB can be related to the sign-reversing pairing potential in the 1-UC FeSe substrate below the islands. The sign reversal is furthermore revealed in a transition of the superconducting gap of FeSe from a U- to a V-like lineshape as the distance between neighboring doublet islands is decreased, indicating the presence of a nodal-like gap as expected for a sign-reversing superconductor. Our configuration of nonmagnetic nanoislands on a high-Tc superconductor for spectroscopy measurements may serve as a local, spatially sensitive, and tunable probe for detecting the sign-reversing order parameter in unconventional superconductors.

cond-mat.supr-con↗

arXiv2024

SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding

Remote Sensing Large Multi-Modal Models (RSLMMs) are developing rapidly and showcase significant capabilities in remote sensing imagery (RSI) comprehension. However, due to the limitations of existing datasets, RSLMMs have shortcomings in understanding the rich semantic relations among objects in complex remote sensing scenes. To unlock RSLMMs' complex comprehension ability, we propose a large-scale instruction tuning dataset FIT-RS, containing 1,800,851 instruction samples. FIT-RS covers common interpretation tasks and innovatively introduces several complex comprehension tasks of escalating difficulty, ranging from relation reasoning to image-level scene graph generation. Based on FIT-RS, we build the FIT-RSFG benchmark. Furthermore, we establish a new benchmark to evaluate the fine-grained relation comprehension capabilities of LMMs, named FIT-RSRC. Based on combined instruction data, we propose SkySenseGPT, which achieves outstanding performance on both public datasets and FIT-RSFG, surpassing existing RSLMMs. We hope the FIT-RS dataset can enhance the relation comprehension capability of RSLMMs and provide a large-scale fine-grained data source for the remote sensing community. The dataset will be available at https://github.com/Luo-Z13/SkySenseGPT

cs.CV↗

arXiv2024

Soli-enabled Noncontact Heart Rate Detection for Sleep and Meditation Tracking

Heart rate (HR) is a crucial physiological signal that can be used to monitor health and fitness. Traditional methods for measuring HR require wearable devices, which can be inconvenient or uncomfortable, especially during sleep and meditation. Noncontact HR detection methods employing microwave radar can be a promising alternative. However, the existing approaches in the literature usually use high-gain antennas and require the sensor to face the user's chest or back, making them difficult to integrate into a portable device and unsuitable for sleep and meditation tracking applications. This study presents a novel approach for noncontact HR detection using a miniaturized Soli radar chip embedded in a portable device (Google Nest Hub). The chip has a $6.5 \mbox{ mm} \times 5 \mbox{ mm} \times 0.9 \mbox{ mm}$ dimension and can be easily integrated into various devices. The proposed approach utilizes advanced signal processing and machine learning techniques to extract HRs from radar signals. The approach is validated on a sleep dataset (62 users, 498 hours) and a meditation dataset (114 users, 1131 minutes). The approach achieves a mean absolute error (MAE) of $1.69$ bpm and a mean absolute percentage error (MAPE) of $2.67\%$ on the sleep dataset. On the meditation dataset, the approach achieves an MAE of $1.05$ bpm and a MAPE of $1.56\%$. The recall rates for the two datasets are $88.53\%$ and $98.16\%$, respectively. This study represents the first application of the noncontact HR detection technology to sleep and meditation tracking, offering a promising alternative to wearable devices for HR monitoring during sleep and meditation.

eess.SP↗

arXiv2024

Polarization-Controlled Chiral Transport

Handedness-selective chiral transport is an intriguing phenomenon that not only holds significant importance for fundamental research, but it also carries application prospects in fields such as optical communications and sensing. Currently, on-chip chiral transport devices are static, unable to modulate the output modes based on the input modes. This limits both device functionality reconfiguration and information transmission capacity. Here, we propose to use the incident polarization diversity to control the Hamiltonian evolution path, achieving polarization-dependent chiral transport. By mapping the evolution path of TE and TM polarizations onto elaborately engineered double-coupled waveguides, we experimentally demonstrate that different polarizations yield controllable modal outputs. This work combines Multiple-Input Multiple-Output and polarization diversity concepts with chiral transport, and challenges the prevailing notion that the modal outputs are fixed to specific modes in chiral transport, thereby opening pathways for the development of on-chip reconfigurable and high-capacity handedness-selective devices.

physics.optics↗

arXiv2024

Explainable AI for Comparative Analysis of Intrusion Detection Models

Explainable Artificial Intelligence (XAI) has become a widely discussed topic, the related technologies facilitate better understanding of conventional black-box models like Random Forest, Neural Networks and etc. However, domain-specific applications of XAI are still insufficient. To fill this gap, this research analyzes various machine learning models to the tasks of binary and multi-class classification for intrusion detection from network traffic on the same dataset using occlusion sensitivity. The models evaluated include Linear Regression, Logistic Regression, Linear Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest, Decision Trees, and Multi-Layer Perceptrons (MLP). We trained all models to the accuracy of 90\% on the UNSW-NB15 Dataset. We found that most classifiers leverage only less than three critical features to achieve such accuracies, indicating that effective feature engineering could actually be far more important for intrusion detection than applying complicated models. We also discover that Random Forest provides the best performance in terms of accuracy, time efficiency and robustness. Data and code available at https://github.com/pcwhy/XML-IntrusionDetection.git

cs.LG↗

arXiv2024

Insulator-to-Metal Transition and Isotropic Gigantic Magnetoresistance in Layered Magnetic Semiconductors

Magnetotransport, the response of electrical conduction to external magnetic field, acts as an important tool to reveal fundamental concepts behind exotic phenomena and plays a key role in enabling spintronic applications. Magnetotransport is generally sensitive to magnetic field orientations. In contrast, efficient and isotropic modulation of electronic transport, which is useful in technology applications such as omnidirectional sensing, is rarely seen, especially for pristine crystals. Here we propose a strategy to realize extremely strong modulation of electron conduction by magnetic field which is independent of field direction. GdPS, a layered antiferromagnetic semiconductor with resistivity anisotropies, supports a field-driven insulator-to-metal transition with a paradoxically isotropic gigantic negative magnetoresistance insensitive to magnetic field orientations. This isotropic magnetoresistance originates from the combined effects of a near-zero spin-orbit coupling of Gd3+-based half-filling f-electron system and the strong on-site f-d exchange coupling in Gd atoms. Our results not only provide a novel material system with extraordinary magnetotransport that offers a missing block for antiferromagnet-based ultrafast and efficient spintronic devices, but also demonstrate the key ingredients for designing magnetic materials with desired transport properties for advanced functionalities.

cond-mat.mtrl-sci↗

arXiv2024

The positive fundamental group of ${\rm Sp}(2n)$

In this paper, we examine the homotopy classes of positive loops in ${\rm Sp}(2n)$. We demonstrate that two positive loops are homotopic if and only if they are homotopic through positive loops. As consequences, we can extend several results of McDuff \cite{McD} and Chance \cite{Cha} to higher dimensional symplectic manifolds without dimensional restrictions.

math.SG↗

arXiv2024

GNNTAL:A Novel Model for Identifying Critical Nodes in Complex Networks

Identification of critical nodes is a prominent topic in the study of complex networks. Numerous methods have been proposed, yet most exhibit inherent limitations. Traditional approaches primarily analyze specific structural features of the network; however, node influence is typically the result of a combination of multiple factors. Machine learning-based methods struggle to effectively represent the complex characteristics of network structures through suitable embedding techniques and require substantial data for training, rendering them prohibitively costly for large-scale networks. To address these challenges, this paper presents an active learning model based on GraphSAGE and Transformer, named GNNTAL. This model is initially pre-trained on random or synthetic networks and subsequently fine-tuned on real-world networks by selecting a few representative nodes using K-Means clustering and uncertainty sampling. This approach offers two main advantages: (1) it significantly reduces training costs; (2) it simultaneously incorporates both local and global features. A series of comparative experiments conducted on twelve real-world networks demonstrate that GNNTAL achieves superior performance. Additionally, this paper proposes an influence maximization method based on the predictions of the GNNTAL model, which achieves optimal performance without the need for complex computations. Finally, the paper analyses certain limitations of the GNNTAL model and suggests potential solutions.

cs.SI↗

arXiv2024

Root Cause Localization for Microservice Systems in Cloud-edge Collaborative Environments

With the development of cloud-native technologies, microservice-based software systems face challenges in accurately localizing root causes when failures occur. Additionally, the cloud-edge collaborative environment introduces more difficulties, such as unstable networks and high latency across network segments. Accurately identifying the root cause of microservices in a cloud-edge collaborative environment has thus become an urgent problem. In this paper, we propose MicroCERCL, a novel approach that pinpoints root causes at the kernel and application level in the cloud-edge collaborative environment. Our key insight is that failures propagate through direct invocations and indirect resource-competition dependencies in a cloud-edge collaborative environment characterized by instability and high latency. This will become more complex in the hybrid deployment that simultaneously involves multiple microservice systems. Leveraging this insight, we extract valid contents from kernel-level logs to prioritize localizing the kernel-level root cause. Moreover, we construct a heterogeneous dynamic topology stack and train a graph neural network model to accurately localize the application-level root cause without relying on historical data. Notably, we released the first benchmark hybrid deployment microservice system in a cloud-edge collaborative environment (the largest and most complex within our knowledge). Experiments conducted on the dataset collected from the benchmark show that MicroCERCL can accurately localize the root cause of microservice systems in such environments, significantly outperforming state-of-the-art approaches with an increase of at least 24.1% in top-1 accuracy.

cs.SE↗

arXiv2024

Electric field controlled valley-polarized photocurrent switch based on the circular bulk photovoltaic effect

Efficient electric manipulation of valley degrees of freedom is critical and challenging for the advancement of valley-based information science and technology. We put forth an electrical scheme, based on a two-band Dirac model, that can switch the fully valley-polarized photocurrent between K and K' valleys using the circular bulk electro-photovoltaic effect. This is accomplished by applying an out-of-plane electric field to the two-dimensional valley materials, which enables continuous tuning of the Berry curvature and its sign flip. We found that the switch of the fully valley-polarized photocurrent is directly tied to the sign change of Berry curvature, which accompanies a topological phase transition, for instance, the quantum spin Hall effect and the quantum valley Hall effect. This scheme has been confirmed in monolayer BiAsI2 and germanene through first-principles calculations. Our paper offers a promising strategy for the development of a volatile valley-addressable memory device and could inspire further research in this area.

cond-mat.mes-hall↗

arXiv2024

Sagiri: Low Dynamic Range Image Enhancement with Generative Diffusion Prior

Capturing High Dynamic Range (HDR) scenery using 8-bit cameras often suffers from over-/underexposure, loss of fine details due to low bit-depth compression, skewed color distributions, and strong noise in dark areas. Traditional LDR image enhancement methods primarily focus on color mapping, which enhances the visual representation by expanding the image's color range and adjusting the brightness. However, these approaches fail to effectively restore content in dynamic range extremes, which are regions with pixel values close to 0 or 255. To address the full scope of challenges in HDR imaging and surpass the limitations of current models, we propose a novel two-stage approach. The first stage maps the color and brightness to an appropriate range while keeping the existing details, and the second stage utilizes a diffusion prior to generate content in dynamic range extremes lost during capture. This generative refinement module can also be used as a plug-and-play module to enhance and complement existing LDR enhancement models. The proposed method markedly improves the quality and details of LDR images, demonstrating superior performance through rigorous experimental validation. The project page is at https://sagiri0208.github.io

eess.IV↗

arXiv2024

DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformer

Generic Face Image Quality Assessment (GFIQA) evaluates the perceptual quality of facial images, which is crucial in improving image restoration algorithms and selecting high-quality face images for downstream tasks. We present a novel transformer-based method for GFIQA, which is aided by two unique mechanisms. First, a Dual-Set Degradation Representation Learning (DSL) mechanism uses facial images with both synthetic and real degradations to decouple degradation from content, ensuring generalizability to real-world scenarios. This self-supervised method learns degradation features on a global scale, providing a robust alternative to conventional methods that use local patch information in degradation learning. Second, our transformer leverages facial landmarks to emphasize visually salient parts of a face image in evaluating its perceptual quality. We also introduce a balanced and diverse Comprehensive Generic Face IQA (CGFIQA-40k) dataset of 40K images carefully designed to overcome the biases, in particular the imbalances in skin tone and gender representation, in existing datasets. Extensive analysis and evaluation demonstrate the robustness of our method, marking a significant improvement over prior methods.

cs.CV↗

arXiv2024

RobustSAM: Segment Anything Robustly on Degraded Images

Segment Anything Model (SAM) has emerged as a transformative approach in image segmentation, acclaimed for its robust zero-shot segmentation capabilities and flexible prompting system. Nonetheless, its performance is challenged by images with degraded quality. Addressing this limitation, we propose the Robust Segment Anything Model (RobustSAM), which enhances SAM's performance on low-quality images while preserving its promptability and zero-shot generalization. Our method leverages the pre-trained SAM model with only marginal parameter increments and computational requirements. The additional parameters of RobustSAM can be optimized within 30 hours on eight GPUs, demonstrating its feasibility and practicality for typical research laboratories. We also introduce the Robust-Seg dataset, a collection of 688K image-mask pairs with different degradations designed to train and evaluate our model optimally. Extensive experiments across various segmentation tasks and datasets confirm RobustSAM's superior performance, especially under zero-shot conditions, underscoring its potential for extensive real-world application. Additionally, our method has been shown to effectively improve the performance of SAM-based downstream tasks such as single image dehazing and deblurring.

cs.CV↗

arXiv2024

Chiral transport in Compact topological waveguide arrays

Waveguide arrays have a wide range of applications, including optical communication, topological systems, and quantum computing. Chiral transport has broad prospects in optical computing, optical switching, optical isolation, and polarization control. However, the lengths of chiral transmission devices in waveguide arrays are typically very long due to adiabatic limit. We introduce topological protection in encircling exceptional points systems, enabling the larger gap size between the bulk states and topological edge states (TESs). Thus, the restriction from adiabatic limit on the rapid evolution of TESs is eased, thereby significantly reducing the device size. We experimentally demonstrate that the chiral transport has been achieved in a topological waveguide array that is only 75 μm long. Our research fuses the topology with non-Hermitian physics to develop highly-integrated photonic chips for further advance of nano-photonics.

physics.optics↗