arXiv subjects

Juan Wang

Publications and source records attributed to Juan Wang.

At least 55 records · Page 3Linked to original sources

arXiv2024

Map-Free Visual Relocalization Enhanced by Instance Knowledge and Depth Knowledge

Map-free relocalization technology is crucial for applications in autonomous navigation and augmented reality, but relying on pre-built maps is often impractical. It faces significant challenges due to limitations in matching methods and the inherent lack of scale in monocular images. These issues lead to substantial rotational and metric errors and even localization failures in real-world scenarios. Large matching errors significantly impact the overall relocalization process, affecting both rotational and translational accuracy. Due to the inherent limitations of the camera itself, recovering the metric scale from a single image is crucial, as this significantly impacts the translation error. To address these challenges, we propose a map-free relocalization method enhanced by instance knowledge and depth knowledge. By leveraging instance-based matching information to improve global matching results, our method significantly reduces the possibility of mismatching across different objects. The robustness of instance knowledge across the scene helps the feature point matching model focus on relevant regions and enhance matching accuracy. Additionally, we use estimated metric depth from a single image to reduce metric errors and improve scale recovery accuracy. By integrating methods dedicated to mitigating large translational and rotational errors, our approach demonstrates superior performance in map-free relocalization techniques.

cs.CV↗

arXiv2024

Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks

The vulnerability of machine learning models to Membership Inference Attacks (MIAs) has garnered considerable attention in recent years. These attacks determine whether a data sample belongs to the model's training set or not. Recent research has focused on reference-based attacks, which leverage difficulty calibration with independently trained reference models. While empirical studies have demonstrated its effectiveness, there is a notable gap in our understanding of the circumstances under which it succeeds or fails. In this paper, we take a further step towards a deeper understanding of the role of difficulty calibration. Our observations reveal inherent limitations in calibration methods, leading to the misclassification of non-members and suboptimal performance, particularly on high-loss samples. We further identify that these errors stem from an imperfect sampling of the potential distribution and a strong dependence of membership scores on the model parameters. By shedding light on these issues, we propose RAPID: a query-efficient and computation-efficient MIA that directly \textbf{R}e-lever\textbf{A}ges the original membershi\textbf{P} scores to m\textbf{I}tigate the errors in \textbf{D}ifficulty calibration. Our experimental results, spanning 9 datasets and 5 model architectures, demonstrate that RAPID outperforms previous state-of-the-art attacks (e.g., LiRA and Canary offline) across different metrics while remaining computationally efficient. Our observations and analysis challenge the current de facto paradigm of difficulty calibration in high-precision inference, encouraging greater attention to the persistent risks posed by MIAs in more practical scenarios.

cs.CR↗

arXiv2024

MobileIQA: Exploiting Mobile-level Diverse Opinion Network For No-Reference Image Quality Assessment Using Knowledge Distillation

With the rising demand for high-resolution (HR) images, No-Reference Image Quality Assessment (NR-IQA) gains more attention, as it can ecaluate image quality in real-time on mobile devices and enhance user experience. However, existing NR-IQA methods often resize or crop the HR images into small resolution, which leads to a loss of important details. And most of them are of high computational complexity, which hinders their application on mobile devices due to limited computational resources. To address these challenges, we propose MobileIQA, a novel approach that utilizes lightweight backbones to efficiently assess image quality while preserving image details through high-resolution input. MobileIQA employs the proposed multi-view attention learning (MAL) module to capture diverse opinions, simulating subjective opinions provided by different annotators during the dataset annotation process. The model uses a teacher model to guide the learning of a student model through knowledge distillation. This method significantly reduces computational complexity while maintaining high performance. Experiments demonstrate that MobileIQA outperforms novel IQA methods on evaluation metrics and computational efficiency. The code is available at https://github.com/chencn2020/MobileIQA.

cs.CV↗

arXiv2024

LCE: A Framework for Explainability of DNNs for Ultrasound Image Based on Concept Discovery

Explaining the decisions of Deep Neural Networks (DNNs) for medical images has become increasingly important. Existing attribution methods have difficulty explaining the meaning of pixels while existing concept-based methods are limited by additional annotations or specific model structures that are difficult to apply to ultrasound images. In this paper, we propose the Lesion Concept Explainer (LCE) framework, which combines attribution methods with concept-based methods. We introduce the Segment Anything Model (SAM), fine-tuned on a large number of medical images, for concept discovery to enable a meaningful explanation of ultrasound image DNNs. The proposed framework is evaluated in terms of both faithfulness and understandability. We point out deficiencies in the popular faithfulness evaluation metrics and propose a new evaluation metric. Our evaluation of public and private breast ultrasound datasets (BUSI and FG-US-B) shows that LCE performs well compared to commonly-used explainability methods. Finally, we also validate that LCE can consistently provide reliable explanations for more meaningful fine-grained diagnostic tasks in breast ultrasound.

cs.AI↗

arXiv2024

LncRNA-disease association prediction method based on heterogeneous information completion and convolutional neural network

The emerging research shows that lncRNA has crucial research value in a series of complex human diseases. Therefore, the accurate identification of lncRNA-disease associations (LDAs) is very important for the warning and treatment of diseases. However, most of the existing methods have limitations in identifying nonlinear LDAs, and it remains a huge challenge to predict new LDAs. In this paper, a deep learning model based on a heterogeneous network and convolutional neural network (CNN) is proposed for lncRNA-disease association prediction, named HCNNLDA. The heterogeneous network containing the lncRNA, disease, and miRNA nodes, is constructed firstly. The embedding matrix of a lncRNA-disease node pair is constructed according to various biological premises about lncRNAs, diseases, and miRNAs. Then, the low-dimensional feature representation is fully learned by the convolutional neural network. In the end, the XGBoot classifier model is trained to predict the potential LDAs. HCNNLDA obtains a high AUC value of 0.9752 and AUPR of 0.9740 under the 5-fold cross-validation. The experimental results show that the proposed model has better performance than that of several latest prediction models. Meanwhile, the effectiveness of HCNNLDA in identifying novel LDAs is further demonstrated by case studies of three diseases. To sum up, HCNNLDA is a feasible calculation model to predict LDAs.

cs.LG↗

arXiv2024

PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts

Due to the diversity of assessment requirements in various application scenarios for the IQA task, existing IQA methods struggle to directly adapt to these varied requirements after training. Thus, when facing new requirements, a typical approach is fine-tuning these models on datasets specifically created for those requirements. However, it is time-consuming to establish IQA datasets. In this work, we propose a Prompt-based IQA (PromptIQA) that can directly adapt to new requirements without fine-tuning after training. On one hand, it utilizes a short sequence of Image-Score Pairs (ISP) as prompts for targeted predictions, which significantly reduces the dependency on the data requirements. On the other hand, PromptIQA is trained on a mixed dataset with two proposed data augmentation strategies to learn diverse requirements, thus enabling it to effectively adapt to new requirements. Experiments indicate that the PromptIQA outperforms SOTA methods with higher performance and better generalization. The code will be available.

cs.CV↗

arXiv2024

Expansion dynamics of Bose-Einstein condensates in a synthetic magnetic field

We investigate the expansion dynamics of spin-orbit-coupled Bose-Einstein condensates subjected to a synthetic magnetic field, after their release from an external harmonic trap. Our findings reveal that the condensate experiences a spin-dependent rotation and separation due to the rigid-like rotational velocity field, which leads to a spin density deflection. The deflection angle reaches a peak at a time that is inversely related to the frequency of the harmonic trap. When the detuning gradient is below a critical value for vortex nucleation, our analytical results derived from a spinor hydrodynamic theory align closely with numerical results using the coupled Gross-Pitaevskii equations. Beyond this critical value, we also numerically simulated the expansion dynamics of the condensates containing vortices with negative circulation. Our findings highlight the pivotal role of the rigid-like rotational velocity field on the dynamics of the condensate and may stimulate further experimental investigations into the rich superfluid dynamics induced by synthetic magnetic fields.

cond-mat.quant-gas↗

arXiv2024

GMC-IQA: Exploiting Global-correlation and Mean-opinion Consistency for No-reference Image Quality Assessment

Due to the subjective nature of image quality assessment (IQA), assessing which image has better quality among a sequence of images is more reliable than assigning an absolute mean opinion score for an image. Thus, IQA models are evaluated by global correlation consistency (GCC) metrics like PLCC and SROCC, rather than mean opinion consistency (MOC) metrics like MAE and MSE. However, most existing methods adopt MOC metrics to define their loss functions, due to the infeasible computation of GCC metrics during training. In this work, we construct a novel loss function and network to exploit Global-correlation and Mean-opinion Consistency, forming a GMC-IQA framework. Specifically, we propose a novel GCC loss by defining a pairwise preference-based rank estimation to solve the non-differentiable problem of SROCC and introducing a queue mechanism to reserve previous data to approximate the global results of the whole data. Moreover, we propose a mean-opinion network, which integrates diverse opinion features to alleviate the randomness of weight learning and enhance the model robustness. Experiments indicate that our method outperforms SOTA methods on multiple authentic datasets with higher accuracy and generalization. We also adapt the proposed loss to various networks, which brings better performance and more stable training.

cs.CV↗

arXiv2023

All-Dielectric Structural Coloration Empowered by Bound States in the Continuum

The technological requirements of low-power and high-fidelity color displays have been instrumental in driving research into advanced coloration technologies. At the forefront of these developments is the implementation of dye-free coloration techniques, which overcome previous constraints related to insufficient resolution and color fading. In this context, resonant dielectric nanostructures have emerged as a promising paradigm, showing great potential for high efficiency, remarkably high color saturation, wide gamut palette, and realistic image reproduction. However, they still face limitations related to color accuracy, purity, and simultaneous brightness tunability. Here, we demonstrate an all-dielectric metasurface empowered by photonic bound states in the continuum (BICs), which supports sharp resonances throughout the visible spectral range, ideally suited for producing a wide range of structural colors. The metasurface design consists of titanium dioxide (TiO2) ellipses with carefully controlled sizes and geometrical asymmetry, allowing versatile and on-demand variation of the brightness and hue of the output colors, respectively.

physics.optics↗

arXiv2023

Insight-HXMT on-orbit thermal control status and thermal deformation impact analysis

Purpose: The Hard X-ray Modulation Telescope is China's first X-ray astronomy satellite launched on June 15th, 2017, dubbed Insight-HXMT. Active and passive thermal control measures are employed to keep devices at suitable temperatures. In this paper, we analyzed the on-orbit thermal monitoring data of the first 5 years and investigated the effect of thermal deformation on the point spread function (PSF) of the telescopes. Methods: We examined the data of the on-orbit temperatures measured using 157 thermistors placed on the collimators, detectors and their support structures and compared the results with the thermal control requirements. The thermal deformation was evaluated by the relative orientation of the two star sensors installed on the main support structure. its effect was estimated with evolution of the PSF obtained with calibration scanning observations of the Crab nebula. Conclusion: The on-orbit temperatures met the thermal control requirements thus far, and the effect of thermal deformation on the PSF was negligible after the on-orbit pointing calibration.

astro-ph.IM↗

arXiv2023

In-orbit performance of LE onboard Insight-HXMT in the first 5 years

Purpose: The Low-Energy X-ray telescope (LE) is a main instrument of the Insight-HXMT mission and consists of 96 Swept Charge Devices (SCD) covering the 1-10 keV energy band. The energy gain and resolution are continuously calibrated by analysing Cassiopeia A (Cas A) and blank sky data, while the effective areas are also calibrated with the observations of the Crab Nebula. In this paper, we present the evolution of the in-orbit performances of LE in the first 5 years since launch. Methods: The Insight-HXMT Data Analysis Software package (HXMTDAS) is utilized to extract the spectra of Cas A, blank sky, and Crab Nebula using different Good Time Interval (GTI) selections. We fit a model with a power-law continuum and several Gaussian lines to different ranges of Cas A and blank sky spectra to get peak energies of their lines through xspec. After updating the energy gain calibration in CALibration DataBase (CALDB), we rerun the Cas A data to obtain the energy resolution. An empirical function is used to modify the simulated effective areas so that the background-subtracted spectrum of the Crab Nebula can best match the standard model of the Crab Nebula. Results: The energy gain, resolution, and effective areas are calibrated every month. The corresponding calibration results are duly updated in CALDB, which can be downloaded and used for the analysis of Insight-HXMT data. Simultaneous observations with NuSTAR and NICER can also be used to verify our derived results. Conclusion: LE is a well calibrated X-ray telescope working in 1-10 keV band. The uncertainty of LE gain is less than 20 eV in 2-9 keV band and the uncertainty of LE resolution is less than 15eV. The systematic errors of LE, compared to the model of the Crab Nebula, are lower than 1.5% in 1-10 keV.

astro-ph.IM↗

arXiv2023

The current unbalance in stacked REBCO tapes -- simulations based on a circuit grid model

Unlike low temperature superconducting cables, there is so far no perfect solution for REBCO coated conductors to form a fully transposed high current cable. Every REBCO cable concept must import a stack of tapes to achieve an operating current as high as tens of kiloamperes. The stacked REBCO tapes, no matter whether they are twisted or not, however, have a nature of non-transposing and therefore could result in current unbalance. In this manuscript, the current unbalance and the related electrical characteristics of a cable made of 40 stacked REBCO tapes are studied with an electrical circuit simulation. The differences in splice resistances and tape inductances that are both related to the non-transposed structure of a REBCO stack are considered. Results show that for a 40 cm long termination, a proper method to keep the contact resistivity between each tape and the copper termination around 1e-8 ohmm is crucial to totally avoid current unbalance lowering the cable performance. Surprisingly, the inter-tape current transfer is found to be able to further exacerbate local high current though it does make the overall distribution more balanced. The inductance difference induced current unbalance is only important if local defects exist at long REBCO tapes, which on the other hand can be cured by good inter-tape current transfer. For a fast-charging rate of 1 kA/s, the inter-tape contact resistivity should also be low to a level of 1e-8 ohmm to ensure a short current transfer length of around 1 m.

physics.app-ph↗

arXiv2023

Weakly Supervised Image Segmentation Beyond Tight Bounding Box Annotations

Weakly supervised image segmentation approaches in the literature usually achieve high segmentation performance using tight bounding box supervision and decrease the performance greatly when supervised by loose bounding boxes. However, compared with loose bounding box, it is much more difficult to acquire tight bounding box due to its strict requirements on the precise locations of the four sides of the box. To resolve this issue, this study investigates whether it is possible to maintain good segmentation performance when loose bounding boxes are used as supervision. For this purpose, this work extends our previous parallel transformation based multiple instance learning (MIL) for tight bounding box supervision by integrating an MIL strategy based on polar transformation to assist image segmentation. The proposed polar transformation based MIL formulation works for both tight and loose bounding boxes, in which a positive bag is defined as pixels in a polar line of a bounding box with one endpoint located inside the object enclosed by the box and the other endpoint located at one of the four sides of the box. Moreover, a weighted smooth maximum approximation is introduced to incorporate the observation that pixels closer to the origin of the polar transformation are more likely to belong to the object in the box. The proposed approach was evaluated on two public datasets using dice coefficient when bounding boxes at different precision levels were considered in the experiments. The results demonstrate that the proposed approach achieves state-of-the-art performance for bounding boxes at all precision levels and is robust to mild and moderate errors in the loose bounding box annotations. The codes are available at \url{https://github.com/wangjuan313/wsis-beyond-tightBB}.

cs.CV↗

arXiv2023

Dimension approximation in smooth dynamical systems

For a non-conformal repeller $Λ$ of a $C^{1+α}$ map $f$ preserving an ergodic measure $μ$ of positive entropy, this paper shows that the Lyapunov dimension of $μ$ can be approximated gradually by the Carathéodory singular dimension of a sequence of horseshoes. For a $C^{1+α}$ diffeomorphism $f$ preserving a hyperbolic ergodic measure $μ$ of positive entropy, if $(f, μ)$ has only two Lyapunov exponents $λ_u(μ)>0>λ_s(μ)$, then the Hausdorff or lower box or upper box dimension of $μ$ can be approximated by the corresponding dimension of the horseshoes $\{Λ_n\}$. The same statement holds true if $f$ is a $C^1$ diffeomorphism with a dominated Oseledet's splitting with respect to $μ$.

math.DS↗

arXiv2022

Resonantly Enhanced Electric-Field Sensing of Etchless Thin Film Lithium Niobate via Quasibound Sates in the Continuum

Electric field detection has been widely utilized in many fields such as scientific research and integrated circuits. To enhance the tuning sensitivity of E-field sensor, in this paper, we theoretically proposed a highly sensitive E-field sensor composed of etchless lithium niobate (LN) material and hybrid coupling-grating systems in the visible near-infrared regime. Such configuration supports high-quality factor quasi-BIC resonance, which generates strong localized field confinement. Due to the large electro-optic coefficient of LN material, one can shift the wavelength and reflection ratio of resonance by tuning the refractive index of LN material. An analytical theory is carried out to explain the relationship between the refractive index variations and the applied voltages, so we successfully obtained a tuning sensitivity of 40.8 nm/V and a minimum detectable electric field amplitude of 24.5 mV with wavelength resolution of 1 nm. Due to the low parasitic capacitance of LN material and high conductivity of gold film and ITO layer which are utilized as the electrodes, the 3dB bandwidth of the devices should exceed 154 GHz. And we believe that such a surface-normal E-field sensor has extensive potential for the extremely weak electric field detection.

physics.optics↗

arXiv2022

CDRNet: Accurate Cup-to-Disc Ratio Measurement with Tight Bounding Box Supervision in Fundus Photography Using Deep Learning

The cup-to-disc ratio (CDR) is one of the most significant indicator for glaucoma diagnosis. Different from the use of costly fully supervised learning formulation with pixel-wise annotations in the literature, this study investigates the feasibility of accurate CDR measurement in fundus images using only tight bounding box supervision. For this purpose, we develop a two-task network named as CDRNet for accurate CDR measurement, one for weakly supervised image segmentation, and the other for bounding-box regression. The weakly supervised image segmentation task is implemented based on generalized multiple instance learning formulation and smooth maximum approximation, and the bounding-box regression task outputs class-specific bounding box prediction in a single scale at the original image resolution. To get accurate bounding box prediction, a class-specific bounding-box normalizer and an expected intersection-over-union are proposed. In the experiments, the proposed approach was evaluated by a testing set with 1200 images using CDR error and $F_1$ score for CDR measurement and dice coefficient for image segmentation. A grader study was conducted to compare the performance of the proposed approach with those of individual graders. The experimental results indicate that the proposed approach outperforms the state-of-the-art performance obtained from the fully supervised image segmentation (FSIS) approach using pixel-wise annotation for CDR measurement. Its performance is also better than those of individual graders. In addition, the proposed approach gets performance close to the state-of-the-art obtained from FSIS and the performance of individual graders for optic cup and disc segmentation. The codes are available at \url{https://github.com/wangjuan313/CDRNet}.

cs.CV↗

arXiv2022

Mirror-coupled plasmonic bound states in the continuum for tunable perfect absorption

Tailoring critical light-matter coupling is a fundamental challenge of nanophotonics, impacting diverse fields from higher harmonic generation and energy conversion to surface-enhanced spectroscopy. Plasmonic perfect absorbers (PAs), where resonant antennas couple to their mirror images in adjacent metal films, have been instrumental for obtaining different coupling regimes by tuning the antenna-film distance. However, for on-chip uses, the ideal PA gap size can only match one wavelength, and wide range multispectral approaches remain challenging. Here, we introduce a new paradigm for plasmonic PAs by combining mirror-coupled resonances with the unique loss engineering capabilities of plasmonic bound states in the continuum (BICs). Our BIC-driven PA platform leverages the asymmetry of the constituent meta-atoms as an additional degree of freedom for reaching the critical coupling (CC) condition, delivering resonances with unity absorbance and high quality factors approaching 100 in the mid-infrared. Such a platform holds flexible tuning knobs including asymmetry parameter, dielectric gap, and geometrical scaling factor to precisely control the coupling condition, resonance frequency, and selective enhancement of magnetic and electric fields while maintaining CC. We demonstrate a pixelated PA metasurface with optimal absorption over a broad range of mid-infrared frequencies (950 ~ 2000 1/cm) using only a single spacer layer thickness and apply it for multispectral surface-enhanced molecular spectroscopy in tailored coupling regimes. Our concept greatly expands the capabilities and flexibility of traditional gap-tuned PAs, opening new perspectives for miniaturized sensing platforms towards on-chip and in-situ detection.

physics.optics↗

arXiv2022

Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report

The role of mobile cameras increased dramatically over the past few years, leading to more and more research in automatic image quality enhancement and RAW photo processing. In this Mobile AI challenge, the target was to develop an efficient end-to-end AI-based image signal processing (ISP) pipeline replacing the standard mobile ISPs that can run on modern smartphone GPUs using TensorFlow Lite. The participants were provided with a large-scale Fujifilm UltraISP dataset consisting of thousands of paired photos captured with a normal mobile camera sensor and a professional 102MP medium-format FujiFilm GFX100 camera. The runtime of the resulting models was evaluated on the Snapdragon's 8 Gen 1 GPU that provides excellent acceleration results for the majority of common deep learning ops. The proposed solutions are compatible with all recent mobile GPUs, being able to process Full HD photos in less than 20-50 milliseconds while achieving high fidelity results. A detailed description of all models developed in this challenge is provided in this paper.

cs.CV↗