arXiv subjects

Zhihong Zhang

Publications and source records attributed to Zhihong Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2024

Adapting Amidst Degradation: Cross Domain Li-ion Battery Health Estimation via Physics-Guided Test-Time Training

Health modeling of lithium-ion batteries (LIBs) is crucial for safe and efficient energy management and carries significant socio-economic implications. Although Machine Learning (ML)-based State of Health (SOH) estimation methods have made significant progress in accuracy, the scarcity of high-quality LIB data remains a major obstacle. Existing transfer learning methods for cross-domain LIB SOH estimation have significantly alleviated the labeling burden of target LIB data, however, they still require sufficient unlabeled target data (UTD) for effective adaptation to the target domain. Collecting this UTD is challenging due to the time-consuming nature of degradation experiments. To address this issue, we introduce a practical Test-Time Training framework, BatteryTTT, which adapts the model continually using each UTD collected amidst degradation, thereby significantly reducing data collection time. To fully utilize each UTD, BatteryTTT integrates the inherent physical laws of modern LIBs into self-supervised learning, termed Physcics-Guided Test-Time Training. Additionally, we explore the potential of large language models (LLMs) in battery sequence modeling by evaluating their performance in SOH estimation through model reprogramming and prefix prompt adaptation. The combination of BatteryTTT and LLM modeling, termed GPT4Battery, achieves state-of-the-art generalization results across current LIB benchmarks. Furthermore, we demonstrate the practical value and scalability of our approach by deploying it in our real-world battery management system (BMS) for 300Ah large-scale energy storage LIBs.

cs.LG↗

arXiv2024

Lightweight High-Speed Photography Built on Coded Exposure and Implicit Neural Representation of Videos

The demand for compact cameras capable of recording high-speed scenes with high resolution is steadily increasing. However, achieving such capabilities often entails high bandwidth requirements, resulting in bulky, heavy systems unsuitable for low-capacity platforms. To address this challenge, leveraging a coded exposure setup to encode a frame sequence into a blurry snapshot and subsequently retrieve the latent sharp video presents a lightweight solution. Nevertheless, restoring motion from blur remains a formidable challenge due to the inherent ill-posedness of motion blur decomposition, the intrinsic ambiguity in motion direction, and the diverse motions present in natural videos. In this study, we propose a novel approach to address these challenges by combining the classical coded exposure imaging technique with the emerging implicit neural representation for videos. We strategically embed motion direction cues into the blurry image during the imaging process. Additionally, we develop a novel implicit neural representation based blur decomposition network to sequentially extract the latent video frames from the blurry image, leveraging the embedded motion direction cues. To validate the effectiveness and efficiency of our proposed framework, we conduct extensive experiments using benchmark datasets and real-captured blurry images. The results demonstrate that our approach significantly outperforms existing methods in terms of both quality and flexibility. The code for our work is available at .https://github.com/zhihongz/BDINR

cs.CV↗

arXiv2024

Identifying Speakers and Addressees of Quotations in Novels with Prompt Learning

Quotations in literary works, especially novels, are important to create characters, reflect character relationships, and drive plot development. Current research on quotation extraction in novels primarily focuses on quotation attribution, i.e., identifying the speaker of the quotation. However, the addressee of the quotation is also important to construct the relationship between the speaker and the addressee. To tackle the problem of dataset scarcity, we annotate the first Chinese quotation corpus with elements including speaker, addressee, speaking mode and linguistic cue. We propose prompt learning-based methods for speaker and addressee identification based on fine-tuned pre-trained models. Experiments on both Chinese and English datasets show the effectiveness of the proposed methods, which outperform methods based on zero-shot and few-shot large language models.

cs.CL↗

arXiv2024

Supercharging Federated Learning with Flower and NVIDIA FLARE

Several open-source systems, such as Flower and NVIDIA FLARE, have been developed in recent years while focusing on different aspects of federated learning (FL). Flower is dedicated to implementing a cohesive approach to FL, analytics, and evaluation. Over time, Flower has cultivated extensive strategies and algorithms tailored for FL application development, fostering a vibrant FL community in research and industry. Conversely, FLARE has prioritized the creation of an enterprise-ready, resilient runtime environment explicitly designed for FL applications in production environments. In this paper, we describe our initial integration of both frameworks and show how they can work together to supercharge the FL ecosystem as a whole. Through the seamless integration of Flower and FLARE, applications crafted within the Flower framework can effortlessly operate within the FLARE runtime environment without necessitating any modifications. This initial integration streamlines the process, eliminating complexities and ensuring smooth interoperability between the two platforms, thus enhancing the overall efficiency and accessibility of FL applications.

cs.DC↗

arXiv2024

YNetr: Dual-Encoder architecture on Plain Scan Liver Tumors (PSLT)

Background: Liver tumors are abnormal growths in the liver that can be either benign or malignant, with liver cancer being a significant health concern worldwide. However, there is no dataset for plain scan segmentation of liver tumors, nor any related algorithms. To fill this gap, we propose Plain Scan Liver Tumors(PSLT) and YNetr. Methods: A collection of 40 liver tumor plain scan segmentation datasets was assembled and annotated. Concurrently, we utilized Dice coefficient as the metric for assessing the segmentation outcomes produced by YNetr, having advantage of capturing different frequency information. Results: The YNetr model achieved a Dice coefficient of 62.63% on the PSLT dataset, surpassing the other publicly available model by an accuracy margin of 1.22%. Comparative evaluations were conducted against a range of models including UNet 3+, XNet, UNetr, Swin UNetr, Trans-BTS, COTr, nnUNetv2 (2D), nnUNetv2 (3D fullres), MedNext (2D) and MedNext(3D fullres). Conclusions: We not only proposed a dataset named PSLT(Plain Scan Liver Tumors), but also explored a structure called YNetr that utilizes wavelet transform to extract different frequency information, which having the SOTA in PSLT by experiments.

eess.IV↗

arXiv2024

UniCompress: Enhancing Multi-Data Medical Image Compression with Knowledge Distillation

In the field of medical image compression, Implicit Neural Representation (INR) networks have shown remarkable versatility due to their flexible compression ratios, yet they are constrained by a one-to-one fitting approach that results in lengthy encoding times. Our novel method, ``\textbf{UniCompress}'', innovatively extends the compression capabilities of INR by being the first to compress multiple medical data blocks using a single INR network. By employing wavelet transforms and quantization, we introduce a codebook containing frequency domain information as a prior input to the INR network. This enhances the representational power of INR and provides distinctive conditioning for different image blocks. Furthermore, our research introduces a new technique for the knowledge distillation of implicit representations, simplifying complex model knowledge into more manageable formats to improve compression ratios. Extensive testing on CT and electron microscopy (EM) datasets has demonstrated that UniCompress outperforms traditional INR methods and commercial compression solutions like HEVC, especially in complex and high compression scenarios. Notably, compared to existing INR techniques, UniCompress achieves a 4$\sim$5 times increase in compression speed, marking a significant advancement in the field of medical image compression. Codes will be publicly available.

eess.IV↗

arXiv2024

Empowering Federated Learning for Massive Models with NVIDIA FLARE

In the ever-evolving landscape of artificial intelligence (AI) and large language models (LLMs), handling and leveraging data effectively has become a critical challenge. Most state-of-the-art machine learning algorithms are data-centric. However, as the lifeblood of model performance, necessary data cannot always be centralized due to various factors such as privacy, regulation, geopolitics, copyright issues, and the sheer effort required to move vast datasets. In this paper, we explore how federated learning enabled by NVIDIA FLARE can address these challenges with easy and scalable integration capabilities, enabling parameter-efficient and full supervised fine-tuning of LLMs for natural language processing and biopharmaceutical applications to enhance their accuracy and robustness.

cs.LG↗

arXiv2024

Towards Quantum Graph Neural Networks: An Ego-Graph Learning Approach

Quantum machine learning is a fast-emerging field that aims to tackle machine learning using quantum algorithms and quantum computing. Due to the lack of physical qubits and an effective means to map real-world data from Euclidean space to Hilbert space, most of these methods focus on quantum analogies or process simulations rather than devising concrete architectures based on qubits. In this paper, we propose a novel hybrid quantum-classical algorithm for graph-structured data, which we refer to as the Ego-graph based Quantum Graph Neural Network (egoQGNN). egoQGNN implements the GNN theoretical framework using the tensor product and unity matrix representation, which greatly reduces the number of model parameters required. When controlled by a classical computer, egoQGNN can accommodate arbitrarily sized graphs by processing ego-graphs from the input graph using a modestly-sized quantum device. The architecture is based on a novel mapping from real-world data to Hilbert space. This mapping maintains the distance relations present in the data and reduces information loss. Experimental results show that the proposed method outperforms competitive state-of-the-art models with only 1.68\% parameters compared to those models.

quant-ph↗

arXiv2023

NVIDIA FLARE: Federated Learning from Simulation to Real-World

Federated learning (FL) enables building robust and generalizable AI models by leveraging diverse datasets from multiple collaborators without centralizing the data. We created NVIDIA FLARE as an open-source software development kit (SDK) to make it easier for data scientists to use FL in their research and real-world applications. The SDK includes solutions for state-of-the-art FL algorithms and federated machine learning approaches, which facilitate building workflows for distributed learning across enterprises and enable platform developers to create a secure, privacy-preserving offering for multiparty collaboration utilizing homomorphic encryption or differential privacy. The SDK is a lightweight, flexible, and scalable Python package. It allows researchers to apply their data science workflows in any training libraries (PyTorch, TensorFlow, XGBoost, or even NumPy) in real-world FL settings. This paper introduces the key design principles of NVFlare and illustrates some use cases (e.g., COVID analysis) with customizable FL workflows that implement different privacy-preserving algorithms. Code is available at https://github.com/NVIDIA/NVFlare.

cs.LG↗

arXiv2023

Labeled Subgraph Entropy Kernel

In recent years, kernel methods are widespread in tasks of similarity measuring. Specifically, graph kernels are widely used in fields of bioinformatics, chemistry and financial data analysis. However, existing methods, especially entropy based graph kernels are subject to large computational complexity and the negligence of node-level information. In this paper, we propose a novel labeled subgraph entropy graph kernel, which performs well in structural similarity assessment. We design a dynamic programming subgraph enumeration algorithm, which effectively reduces the time complexity. Specially, we propose labeled subgraph, which enriches substructure topology with semantic information. Analogizing the cluster expansion process of gas cluster in statistical mechanics, we re-derive the partition function and calculate the global graph entropy to characterize the network. In order to test our method, we apply several real-world datasets and assess the effects in different tasks. To capture more experiment details, we quantitatively and qualitatively analyze the contribution of different topology structures. Experimental results successfully demonstrate the effectiveness of our method which outperforms several state-of-the-art methods.

cs.LG↗

arXiv2023

INFWIDE: Image and Feature Space Wiener Deconvolution Network for Non-blind Image Deblurring in Low-Light Conditions

Under low-light environment, handheld photography suffers from severe camera shake under long exposure settings. Although existing deblurring algorithms have shown promising performance on well-exposed blurry images, they still cannot cope with low-light snapshots. Sophisticated noise and saturation regions are two dominating challenges in practical low-light deblurring. In this work, we propose a novel non-blind deblurring method dubbed image and feature space Wiener deconvolution network (INFWIDE) to tackle these problems systematically. In terms of algorithm design, INFWIDE proposes a two-branch architecture, which explicitly removes noise and hallucinates saturated regions in the image space and suppresses ringing artifacts in the feature space, and integrates the two complementary outputs with a subtle multi-scale fusion network for high quality night photograph deblurring. For effective network training, we design a set of loss functions integrating a forward imaging model and backward reconstruction to form a close-loop regularization to secure good convergence of the deep neural network. Further, to optimize INFWIDE's applicability in real low-light conditions, a physical-process-based low-light noise model is employed to synthesize realistic noisy night photographs for model training. Taking advantage of the traditional Wiener deconvolution algorithm's physically driven characteristics and arisen deep neural network's representation ability, INFWIDE can recover fine details while suppressing the unpleasant artifacts during deblurring. Extensive experiments on synthetic data and real data demonstrate the superior performance of the proposed approach.

cs.CV↗

arXiv2023

DarkVision: A Benchmark for Low-light Image/Video Perception

Imaging and perception in photon-limited scenarios is necessary for various applications, e.g., night surveillance or photography, high-speed photography, and autonomous driving. In these cases, cameras suffer from low signal-to-noise ratio, which degrades the image quality severely and poses challenges for downstream high-level vision tasks like object detection and recognition. Data-driven methods have achieved enormous success in both image restoration and high-level vision tasks. However, the lack of high-quality benchmark dataset with task-specific accurate annotations for photon-limited images/videos delays the research progress heavily. In this paper, we contribute the first multi-illuminance, multi-camera, and low-light dataset, named DarkVision, serving for both image enhancement and object detection. We provide bright and dark pairs with pixel-wise registration, in which the bright counterpart provides reliable reference for restoration and annotation. The dataset consists of bright-dark pairs of 900 static scenes with objects from 15 categories, and 32 dynamic scenes with 4-category objects. For each scene, images/videos were captured at 5 illuminance levels using three cameras of different grades, and average photons can be reliably estimated from the calibration data for quantitative studies. The static-scene images and dynamic videos respectively contain around 7,344 and 320,667 instances in total. With DarkVision, we established baselines for image/video enhancement and object detection by representative algorithms. To demonstrate an exemplary application of DarkVision, we propose two simple yet effective approaches for improving performance in video enhancement and object detection respectively. We believe DarkVision would advance the state-of-the-arts in both imaging and related computer vision tasks in low-light environment.

cs.CV↗

arXiv2023

PA-GM: Position-Aware Learning of Embedding Networks for Deep Graph Matching

Graph matching can be formalized as a combinatorial optimization problem, where there are corresponding relationships between pairs of nodes that can be represented as edges. This problem becomes challenging when there are potential ambiguities present due to nodes and edges with high similarity, and there is a need to find accurate results for similar content matching. In this paper, we introduce a novel end-to-end neural network that can map the linear assignment problem into a high-dimensional space augmented with node-level relative position information, which is crucial for improving the method's performance for similar content matching. Our model constructs the anchor set for the relative position of nodes and then aggregates the feature information of the target node and each anchor node based on a measure of relative position. It then learns the node feature representation by integrating the topological structure and the relative position information, thus realizing the linear assignment between the two graphs. To verify the effectiveness and generalizability of our method, we conduct graph matching experiments, including cross-category matching, on different real-world datasets. Comparisons with different baselines demonstrate the superiority of our method. Our source code is available under https://github.com/anonymous.

cs.CV↗

arXiv2022

Strong Second Harmonic Generation from Bilayer Graphene with Symmetry Breaking by Redox-Governed Charge Doping

Missing second-order nonlinearity in centrosymmetric graphene overshadows its intriguing optical attribute. Here, we report redox-governed charge doping could effectively break the centrosymmetry of bilayer graphene (BLG), enabling a strong second harmonic generation (SHG) with a strength close to that of the well-known monolayer MoS2. Verified from control experiments with in situ electrical current annealing and electrically gate-controlled SHG, the required centrosymmetry breaking of the emerging SHG arises from the charge-doping on the bottom layer of BLG by the oxygen/water redox couple. Our results not only reveal that charge doping is an effective way to break the inversion symmetry of BLG despite its strong interlayer coupling but also indicate that SHG spectroscopy is a valid technique to probe molecular doping on two-dimensional materials.

physics.optics↗

arXiv2022

Layer-by-layer growth of bilayer graphene single-crystals enabled by self-transmitting catalytic activity

Direct growth of large-area vertically stacked two-dimensional (2D) van der Waal (vdW) materials is a prerequisite for their high-end applications in integrated electronics, optoelectronics and photovoltaics. Currently, centimetre- to even metre-scale monolayers of single-crystal graphene (MLG) and hexagonal boron nitride (h-BN) have been achieved by epitaxial growth on various single-crystalline substrates. However, in principle, this success in monolayer epitaxy seems extremely difficult to be replicated to bi- or few-layer growth, as the full coverage of the first layer was believed to terminate the reactivity of those adopting catalytic metal surfaces. Here, we report an exceptional layer-by-layer chemical vapour deposition (CVD) growth of large size bi-layer graphene single-crystals, enabled by self-transmitting catalytic activity from platinum (Pt) surfaces to the outermost graphene layers. In-situ growth and real-time surveillance experiments, under well-controlled environments, unambiguously verify that the growth does follow the layer-by-layer mode on open surfaces of MLG/Pt(111). First-principles calculations indicate that the transmittal of catalytic activity is allowed by an appreciable electronic hybridisation between graphene overlayers and Pt surfaces, enabling catalytic dissociation of hydrocarbons and subsequently direct graphitisation of their radicals on the outermost sp2 carbon surface. This self-transmitting catalytic activity is also proven to be robust for tube-furnace CVD in fabricating single-crystalline graphene bi-, tri- and tetra-layers, as well as h-BN few-layers. Our findings offer an exceptional strategy for potential controllable, layer-by-layer and wafer-scale growth of vertically stacked few-layered 2D single crystals.

cond-mat.mtrl-sci↗

arXiv2022

A Dual Sensor Computational Camera for High Quality Dark Videography

Videos captured under low light conditions suffer from severe noise. A variety of efforts have been devoted to image/video noise suppression and made large progress. However, in extremely dark scenarios, extensive photon starvation would hamper precise noise modeling. Instead, developing an imaging system collecting more photons is a more effective way for high-quality video capture under low illuminations. In this paper, we propose to build a dual-sensor camera to additionally collect the photons in NIR wavelength, and make use of the correlation between RGB and near-infrared (NIR) spectrum to perform high-quality reconstruction from noisy dark video pairs. In hardware, we build a compact dual-sensor camera capturing RGB and NIR videos simultaneously. Computationally, we propose a dual-channel multi-frame attention network (DCMAN) utilizing spatial-temporal-spectral priors to reconstruct the low-light RGB and NIR videos. In addition, we build a high-quality paired RGB and NIR video dataset, based on which the approach can be applied to different sensors easily by training the DCMAN model with simulated noisy input following a physical-process-based CMOS noise model. Both experiments on synthetic and real videos validate the performance of this compact dual-sensor camera design and the corresponding reconstruction algorithm in dark videography.

eess.IV↗

arXiv2022

Two-level Graph Neural Network

Graph Neural Networks (GNNs) are recently proposed neural network structures for the processing of graph-structured data. Due to their employed neighbor aggregation strategy, existing GNNs focus on capturing node-level information and neglect high-level information. Existing GNNs therefore suffer from representational limitations caused by the Local Permutation Invariance (LPI) problem. To overcome these limitations and enrich the features captured by GNNs, we propose a novel GNN framework, referred to as the Two-level GNN (TL-GNN). This merges subgraph-level information with node-level information. Moreover, we provide a mathematical analysis of the LPI problem which demonstrates that subgraph-level information is beneficial to overcoming the problems associated with LPI. A subgraph counting method based on the dynamic programming algorithm is also proposed, and this has time complexity is O(n^3), n is the number of nodes of a graph. Experiments show that TL-GNN outperforms existing GNNs and achieves state-of-the-art performance.

cs.LG↗

arXiv2021

Minority Oversampling for Imbalanced Time Series Classification

Many important real-world applications involve time-series data with skewed distribution. Compared to conventional imbalance learning problems, the classification of imbalanced time-series data is more challenging due to high dimensionality and high inter-variable correlation. This paper proposes a structure preserving Oversampling method to combat the High-dimensional Imbalanced Time-series classification (OHIT). OHIT first leverages a density-ratio based shared nearest neighbor clustering algorithm to capture the modes of minority class in high-dimensional space. It then for each mode applies the shrinkage technique of large-dimensional covariance matrix to obtain accurate and reliable covariance structure. Finally, OHIT generates the structure-preserving synthetic samples based on multivariate Gaussian distribution by using the estimated covariance matrices. Experimental results on several publicly available time-series datasets (including unimodal and multimodal) demonstrate the superiority of OHIT against the state-of-the-art oversampling algorithms in terms of F1, G-mean, and AUC.

cs.LG↗