Searcharxiv⌕ Search

arXiv subjects

Fan Zhang

Publications and source records attributed to Fan Zhang.

At least 541 records · Page 30Linked to original sources
arXiv2024

A Deep Network for Explainable Prediction of Non-Imaging Phenotypes using Anatomical Multi-View Data

Large datasets often contain multiple distinct feature sets, or views, that offer complementary information that can be exploited by multi-view learning methods to improve results. We investigate anatomical multi-view data, where each brain anatomical structure is described with multiple feature sets. In particular, we focus on sets of white matter microstructure and connectivity features from diffusion MRI, as well as sets of gray matter area and thickness features from structural MRI. We investigate machine learning methodology that applies multi-view approaches to improve the prediction of non-imaging phenotypes, including demographics (age), motor (strength), and cognition (picture vocabulary). We present an explainable multi-view network (EMV-Net) that can use different anatomical views to improve prediction performance. In this network, each individual anatomical view is processed by a view-specific feature extractor and the extracted information from each view is fused using a learnable weight. This is followed by a wavelet transform-based module to obtain complementary information across views which is then applied to calibrate the view-specific information. Additionally, the calibrator produces an attention-based calibration score to indicate anatomical structures' importance for interpretation.

q-bio.QM↗
arXiv2024

Gravity-driven magnetogenesis

Structure formation heralds the era of deviation of the matter content of the Universe away from thermal equilibrium, so the gravitational contribution to entropy, in the form of Weyl curvature, must become active in order for the overall entropy of the Universe to remain increasing. The tidal and frame dragging sectors of the Weyl tensor must inevitably both be present in this dynamic environment, as they mutually induce each other. The frame dragging effect is able to impress vorticity onto the plasma current arising due to the mass disparity between electrons and protons, which in turn begets a magnetic field from none. We show that this gravity-driven magnetogenesis mechanism, besides being able to operate outside of galaxies, thus facilitate large coherence length scales, may be able to generate the field strength necessary to seed dynamo processes.

astro-ph.CO↗
arXiv2023

The Energy Response of LaBr3(Ce), LaBr3(Ce,Sr) and NaI(Tl) Crystals for GECAM

The GECAM series of satellites utilize LaBr3(Ce), LaBr3(Ce,Sr), and NaI(Tl) crystals as sensitive materials for gamma-ray detectors (GRDs). To investigate the non-linearity in the detection of low-energy gamma rays and address errors in the E-C relationship calibration, comprehensive tests and comparative studies of the non-linearity of these three crystals were conducted using Compton electrons, radioactive sources, and mono-energetic X-rays. The non-linearity test results for Compton electrons and X-rays displayed substantial differences, with all three crystals showing higher non-linearity for X-rays and gamma-rays than for Compton electrons. Despite LaBr3(Ce) and LaBr3(Ce,Sr) crystals having higher absolute light yields, they exhibited a noticeable non-linear decrease in light yield, especially at energies below 400 keV. The NaI(Tl) crystal demonstrated excess light output in the 6~200 keV range, reaching a maximum excess of 9.2% at 30 keV in X-ray testing and up to 15.5% at 14 keV during Compton electron testing, indicating a significant advantage in the detection of low-energy gamma rays. Furthermore, this paper explores the underlying causes of the observed non-linearity in these crystals. This study not only elucidates the detector responses of GECAM, but also marks the inaugural comprehensive investigation into the non-linearity of domestically produced lanthanum bromide and sodium iodide crystals.

physics.ins-det↗
arXiv2023

Emage: Non-Autoregressive Text-to-Image Generation

Autoregressive and diffusion models drive the recent breakthroughs on text-to-image generation. Despite their huge success of generating high-realistic images, a common shortcoming of these models is their high inference latency - autoregressive models run more than a thousand times successively to produce image tokens and diffusion models convert Gaussian noise into images with many hundreds of denoising steps. In this work, we explore non-autoregressive text-to-image models that efficiently generate hundreds of image tokens in parallel. We develop many model variations with different learning and inference strategies, initialized text encoders, etc. Compared with autoregressive baselines that needs to run one thousand times, our model only runs 16 times to generate images of competitive quality with an order of magnitude lower inference latency. Our non-autoregressive model with 346M parameters generates an image of 256$\times$256 with about one second on one V100 GPU.

cs.CV↗
arXiv2023

Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion

Monocular depth estimation has experienced significant progress on terrestrial images in recent years, largely due to deep learning advancements. However, it remains inadequate for underwater scenes, primarily because of data scarcity. Given the inherent challenges of light attenuation and backscattering in water, acquiring clear underwater images or precise depth information is notably difficult and costly. Consequently, learning-based approaches often rely on synthetic data or turn to unsupervised or self-supervised methods to mitigate this lack of data. Nonetheless, the performance of these methods is often constrained by the domain gap and looser constraints. In this paper, we propose a novel pipeline for generating photorealistic underwater images using accurate terrestrial depth data. This approach facilitates the training of supervised models for underwater depth estimation, effectively reducing the performance disparity between terrestrial and underwater environments. Contrary to prior synthetic datasets that merely apply style transfer to terrestrial images without altering the scene content, our approach uniquely creates vibrant, non-existent underwater scenes by leveraging terrestrial depth data through the innovative Stable Diffusion model. Specifically, we introduce a unique Depth2Underwater ControlNet, trained on specially prepared \{Underwater, Depth, Text\} data triplets, for this generation task. Our newly developed dataset enables terrestrial depth estimation models to achieve considerable improvements, both quantitatively and qualitatively, on unseen underwater images, surpassing their terrestrial pre-trained counterparts. Moreover, the enhanced depth accuracy for underwater scenes also aids underwater image restoration techniques that rely on depth maps, further demonstrating our dataset's utility. The dataset will be available at https://github.com/zkawfanx/Atlantis.

cs.CV↗
arXiv2023

Full-reference Video Quality Assessment for User Generated Content Transcoding

Unlike video coding for professional content, the delivery pipeline of User Generated Content (UGC) involves transcoding where unpristine reference content needs to be compressed repeatedly. In this work, we observe that existing full-/no-reference quality metrics fail to accurately predict the perceptual quality difference between transcoded UGC content and the corresponding unpristine references. Therefore, they are unsuited for guiding the rate-distortion optimisation process in the transcoding process. In this context, we propose a bespoke full-reference deep video quality metric for UGC transcoding. The proposed method features a transcoding-specific weakly supervised training strategy employing a quality ranking-based Siamese structure. The proposed method is evaluated on the YouTube-UGC VP9 subset and the LIVE-Wild database, demonstrating state-of-the-art performance compared to existing VQA methods.

eess.IV↗
arXiv2023

Device Scheduling for Relay-assisted Over-the-Air Aggregation in Federated Learning

Federated learning (FL) leverages data distributed at the edge of the network to enable intelligent applications. The efficiency of FL can be improved by using over-the-air computation (AirComp) technology in the process of gradient aggregation. In this paper, we propose a relay-assisted large-scale FL framework, and investigate the device scheduling problem in relay-assisted FL systems under the constraints of power consumption and mean squared error (MSE). we formulate a joint device scheduling, and power allocation problem to maximize the number of scheduled devices. We solve the resultant non-convex optimization problem by transforming the optimization problem into multiple sparse optimization problems. By the proposed device scheduling algorithm, these sparse sub-problems are solved and the maximum number of federated learning edge devices is obtained. The simulation results demonstrate the effectiveness of the proposed scheme as compared with other benchmark schemes.

cs.LG↗
arXiv2023

Improving the quantification of overshooting shock-capturing oscillations

An approach for quantitatively evaluating overshooting oscillations is designed to characterize the performance of shock-capturing schemes. Specifically, following our previous work focused on cases with only discontinuities, now we account for the concurrent presences of discontinuities and smooth waves, each with a complete set of supported modes on a given discretization. The linear advection equation is taken as the model equation, and a standardized measurement is given for overshooting oscillations produced by shock-capturing schemes. Thereby, we can quantitatively reveal the shock-capturing robustness of, for example, weighted essentially non-oscillatory schemes, by comparing and analyzing the resulting overshoots. In particular, we are able to find out the ranges of wavenumbers in which the numerical schemes are especially prone to produce overshooting oscillations. While lower dissipation is usually anticipated for high-order schemes, we provide a simple measurement for evaluating the shock-capturing robustness, which was not trivial due to the nonlinearity of shock-capturing computations.

physics.flu-dyn↗
arXiv2023

LDMVFI: Video Frame Interpolation with Latent Diffusion Models

Existing works on video frame interpolation (VFI) mostly employ deep neural networks that are trained by minimizing the L1, L2, or deep feature space distance (e.g. VGG loss) between their outputs and ground-truth frames. However, recent works have shown that these metrics are poor indicators of perceptual VFI quality. Towards developing perceptually-oriented VFI methods, in this work we propose latent diffusion model-based VFI, LDMVFI. This approaches the VFI problem from a generative perspective by formulating it as a conditional generation problem. As the first effort to address VFI using latent diffusion models, we rigorously benchmark our method on common test sets used in the existing VFI literature. Our quantitative experiments and user study indicate that LDMVFI is able to interpolate video content with favorable perceptual quality compared to the state of the art, even in the high-resolution regime. Our code is available at https://github.com/danier97/LDMVFI.

eess.IV↗
arXiv2023

Fed-urlBERT: Client-side Lightweight Federated Transformers for URL Threat Analysis

In evolving cyber landscapes, the detection of malicious URLs calls for cooperation and knowledge sharing across domains. However, collaboration is often hindered by concerns over privacy and business sensitivities. Federated learning addresses these issues by enabling multi-clients collaboration without direct data exchange. Unfortunately, if highly expressive Transformer models are used, clients may face intolerable computational burdens, and the exchange of weights could quickly deplete network bandwidth. In this paper, we propose Fed-urlBERT, a federated URL pre-trained model designed to address both privacy concerns and the need for cross-domain collaboration in cybersecurity. Fed-urlBERT leverages split learning to divide the pre-training model into client and server part, so that the client part takes up less extensive computation resources and bandwidth. Our appraoch achieves performance comparable to centralized model under both independently and identically distributed (IID) and two non-IID data scenarios. Significantly, our federated model shows about an 7% decrease in the FPR compared to the centralized model. Additionally, we implement an adaptive local aggregation strategy that mitigates heterogeneity among clients, demonstrating promising performance improvements. Overall, our study validates the applicability of the proposed Transformer federated learning for URL threat analysis, establishing a foundation for real-world collaborative cybersecurity efforts. The source code is accessible at https://github.com/Davidup1/FedURLBERT.

cs.CR↗
arXiv2023

A Simple Framework to Enhance the Adversarial Robustness of Deep Learning-based Intrusion Detection System

Deep learning based intrusion detection systems (DL-based IDS) have emerged as one of the best choices for providing security solutions against various network intrusion attacks. However, due to the emergence and development of adversarial deep learning technologies, it becomes challenging for the adoption of DL models into IDS. In this paper, we propose a novel IDS architecture that can enhance the robustness of IDS against adversarial attacks by combining conventional machine learning (ML) models and Deep Learning models. The proposed DLL-IDS consists of three components: DL-based IDS, adversarial example (AE) detector, and ML-based IDS. We first develop a novel AE detector based on the local intrinsic dimensionality (LID). Then, we exploit the low attack transferability between DL models and ML models to find a robust ML model that can assist us in determining the maliciousness of AEs. If the input traffic is detected as an AE, the ML-based IDS will predict the maliciousness of input traffic, otherwise the DL-based IDS will work for the prediction. The fusion mechanism can leverage the high prediction accuracy of DL models and low attack transferability between DL models and ML models to improve the robustness of the whole system. In our experiments, we observe a significant improvement in the prediction performance of the IDS when subjected to adversarial attack, achieving high accuracy with low resource consumption.

cs.CR↗
arXiv2023

Accelerating Learnt Video Codecs with Gradient Decay and Layer-wise Distillation

In recent years, end-to-end learnt video codecs have demonstrated their potential to compete with conventional coding algorithms in term of compression efficiency. However, most learning-based video compression models are associated with high computational complexity and latency, in particular at the decoder side, which limits their deployment in practical applications. In this paper, we present a novel model-agnostic pruning scheme based on gradient decay and adaptive layer-wise distillation. Gradient decay enhances parameter exploration during sparsification whilst preventing runaway sparsity and is superior to the standard Straight-Through Estimation. The adaptive layer-wise distillation regulates the sparse training in various stages based on the distortion of intermediate features. This stage-wise design efficiently updates parameters with minimal computational overhead. The proposed approach has been applied to three popular end-to-end learnt video codecs, FVC, DCVC, and DCVC-HEM. Results confirm that our method yields up to 65% reduction in MACs and 2x speed-up with less than 0.3dB drop in BD-PSNR. Supporting code and supplementary material can be downloaded from: https://jasminepp.github.io/lightweightdvc/

eess.IV↗
arXiv2023

MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition

Recently, multi-expert methods have led to significant improvements in long-tail recognition (LTR). We summarize two aspects that need further enhancement to contribute to LTR boosting: (1) More diverse experts; (2) Lower model variance. However, the previous methods didn't handle them well. To this end, we propose More Diverse experts with Consistency Self-distillation (MDCS) to bridge the gap left by earlier methods. Our MDCS approach consists of two core components: Diversity Loss (DL) and Consistency Self-distillation (CS). In detail, DL promotes diversity among experts by controlling their focus on different categories. To reduce the model variance, we employ KL divergence to distill the richer knowledge of weakly augmented instances for the experts' self-distillation. In particular, we design Confident Instance Sampling (CIS) to select the correctly classified instances for CS to avoid biased/noisy knowledge. In the analysis and ablation study, we demonstrate that our method compared with previous work can effectively increase the diversity of experts, significantly reduce the variance of the model, and improve recognition accuracy. Moreover, the roles of our DL and CS are mutually reinforcing and coupled: the diversity of experts benefits from the CS, and the CS cannot achieve remarkable results without the DL. Experiments show our MDCS outperforms the state-of-the-art by 1% $\sim$ 2% on five popular long-tailed benchmarks, including CIFAR10-LT, CIFAR100-LT, ImageNet-LT, Places-LT, and iNaturalist 2018. The code is available at https://github.com/fistyee/MDCS.

cs.CV↗
arXiv2023

GPUSCAN$^{++}$:Efficient Structural Graph Clustering on GPUs

Structural clustering is one of the most popular graph clustering methods, which has achieved great performance improvement by utilizing GPUs. Even though, the state-of-the-art GPU-based structural clustering algorithm, GPUSCAN, still suffers from efficiency issues since lots of extra costs are introduced for parallelization. Moreover, GPUSCAN assumes that the graph is resident in the GPU memory. However, the GPU memory capacity is limited currently while many real-world graphs are big and cannot fit in the GPU memory, which makes GPUSCAN unable to handle large graphs. Motivated by this, we present a new GPU-based structural clustering algorithm, GPUSCAN++, in this paper. To address the efficiency issue, we propose a new progressive clustering method tailored for GPUs that not only avoid high parallelization costs but also fully exploits the computing resources of GPUs. To address the GPU memory limitation issue, we propose a partition-based algorithm for structural clustering that can process large graphs with limited GPU memory. We conduct experiments on real graphs, and the experimental results demonstrate that our algorithm can achieve up to 168 times speedup compared with the state-of-the-art GPU-based algorithm when the graph can be resident in the GPU memory. Moreover, our algorithm is scalable to handle large graphs. As an example, our algorithm can finish the structural clustering on a graph with 1.8 billion edges using less than 2 GB GPU memory.

cs.DB↗
arXiv2023

How does spatial structure affect psychological restoration? A method based on Graph Neural Networks and Street View Imagery

The Attention Restoration Theory (ART) presents a theoretical framework with four essential indicators (being away, extent, fascinating, and compatibility) for comprehending urban and natural restoration quality. However, previous studies relied on non-sequential data and non-spatial dependent methods, which overlooks the impact of spatial structure defined here as the positional relationships between scene entities on restoration quality. The past methods also make it challenging to measure restoration quality on an urban scale. In this work, a spatial-dependent graph neural networks (GNNs) approach is proposed to reveal the relation between spatial structure and restoration quality on an urban scale. Specifically, we constructed two different types of graphs at the street and city levels. The street-level graphs, using sequential street view images (SVIs) of road segments to capture position relationships between entities, were used to represent spatial structure. The city-level graph, modeling the topological relationships of roads as non-Euclidean data structures and embedding urban features (including Perception-features, Spatial-features, and Socioeconomic-features), was used to measure restoration quality. The results demonstrate that: 1) spatial-dependent GNNs model outperforms traditional methods (Acc = 0.735, F1 = 0.732); 2) spatial structure portrayed through sequential SVIs data significantly influences restoration quality; 3) spaces with the same restoration quality exhibited distinct spatial structures patterns. This study clarifies the association between spatial structure and restoration quality, providing a new perspective to improve urban well-being in the future.

cs.CV↗
arXiv2023

The density-functional theory of quantum droplets

In quantum droplets, the mean-field energy is comparable to the Lee-Huang-Yang (LHY) energy. In the Bogoliubov theory, the LHY energy of the quantum droplet has an imaginary part, but it is neglected for practical purposes. So far, most theoretical studies of quantum droplets have been based on the extended Gross-Pitaevskii (GP) equation obtained by adding the LHY energy to the GP equation. In this article, we present the density-functional theory of quantum droplets. In our approach, the quantum fluctuations in quantum droplets, as described by an effective action, generate the correlation energy which is real and can be determined self-consistently. Using the density-functional theory, we calculate higher-order corrections to the energy, the quantum depletion fraction, and the excitations of the droplet. Our results for the ground-state energy and the quantum depletion fraction are compared with the Monte Carlo results and good agreement is found. The implications of our theory are discussed.

quant-ph↗
arXiv2023

VBench: Comprehensive Benchmark Suite for Video Generative Models

Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align with human perceptions; 2) An ideal evaluation system should provide insights to inform future developments of video generation. To this end, we present VBench, a comprehensive benchmark suite that dissects "video generation quality" into specific, hierarchical, and disentangled dimensions, each with tailored prompts and evaluation methods. VBench has three appealing properties: 1) Comprehensive Dimensions: VBench comprises 16 dimensions in video generation (e.g., subject identity inconsistency, motion smoothness, temporal flickering, and spatial relationship, etc). The evaluation metrics with fine-grained levels reveal individual models' strengths and weaknesses. 2) Human Alignment: We also provide a dataset of human preference annotations to validate our benchmarks' alignment with human perception, for each evaluation dimension respectively. 3) Valuable Insights: We look into current models' ability across various evaluation dimensions, and various content types. We also investigate the gaps between video and image generation models. We will open-source VBench, including all prompts, evaluation methods, generated videos, and human preference annotations, and also include more video generation models in VBench to drive forward the field of video generation.

cs.CV↗