Search arXiv⌕ Search

arXiv subjects

Kai Zhang

Publications and source records attributed to Kai Zhang.

At least 433 records · Page 24Linked to original sources
arXiv2023

Survey on Deep Face Restoration: From Non-blind to Blind and Beyond

Face restoration (FR) is a specialized field within image restoration that aims to recover low-quality (LQ) face images into high-quality (HQ) face images. Recent advances in deep learning technology have led to significant progress in FR methods. In this paper, we begin by examining the prevalent factors responsible for real-world LQ images and introduce degradation techniques used to synthesize LQ images. We also discuss notable benchmarks commonly utilized in the field. Next, we categorize FR methods based on different tasks and explain their evolution over time. Furthermore, we explore the various facial priors commonly utilized in the restoration process and discuss strategies to enhance their effectiveness. In the experimental section, we thoroughly evaluate the performance of state-of-the-art FR methods across various tasks using a unified benchmark. We analyze their performance from different perspectives. Finally, we discuss the challenges faced in the field of FR and propose potential directions for future advancements. The open-source repository corresponding to this work can be found at https:// github.com/ 24wenjie-li/ Awesome-Face-Restoration.

cs.CV↗
arXiv2023

Automatic Evaluation of Attribution by Large Language Models

A recent focus of large language model (LLM) development, as exemplified by generative search engines, is to incorporate external references to generate and support its claims. However, evaluating the attribution, i.e., verifying whether the generated statement is fully supported by the cited reference, remains an open problem. Although human evaluation is common practice, it is costly and time-consuming. In this paper, we investigate the automatic evaluation of attribution given by LLMs. We begin by defining different types of attribution errors, and then explore two approaches for automatic evaluation: prompting LLMs and fine-tuning smaller LMs. The fine-tuning data is repurposed from related tasks such as question answering, fact-checking, natural language inference, and summarization. We manually curate a set of test examples covering 12 domains from a generative search engine, New Bing. Our results on this curated test set and simulated examples from existing benchmarks highlight both promising signals and challenges. We hope our problem formulation, testbeds, and findings will help lay the foundation for future studies on this important problem.

cs.CL↗
arXiv2023

Multi-Task Learning for Post-transplant Cause of Death Analysis: A Case Study on Liver Transplant

Organ transplant is the essential treatment method for some end-stage diseases, such as liver failure. Analyzing the post-transplant cause of death (CoD) after organ transplant provides a powerful tool for clinical decision making, including personalized treatment and organ allocation. However, traditional methods like Model for End-stage Liver Disease (MELD) score and conventional machine learning (ML) methods are limited in CoD analysis due to two major data and model-related challenges. To address this, we propose a novel framework called CoD-MTL leveraging multi-task learning to model the semantic relationships between various CoD prediction tasks jointly. Specifically, we develop a novel tree distillation strategy for multi-task learning, which combines the strength of both the tree model and multi-task learning. Experimental results are presented to show the precise and reliable CoD predictions of our framework. A case study is conducted to demonstrate the clinical importance of our method in the liver transplant.

cs.LG↗
arXiv2023

Multimodal Question Answering for Unified Information Extraction

Multimodal information extraction (MIE) aims to extract structured information from unstructured multimedia content. Due to the diversity of tasks and settings, most current MIE models are task-specific and data-intensive, which limits their generalization to real-world scenarios with diverse task requirements and limited labeled data. To address these issues, we propose a novel multimodal question answering (MQA) framework to unify three MIE tasks by reformulating them into a unified span extraction and multi-choice QA pipeline. Extensive experiments on six datasets show that: 1) Our MQA framework consistently and significantly improves the performances of various off-the-shelf large multimodal models (LMM) on MIE tasks, compared to vanilla prompting. 2) In the zero-shot setting, MQA outperforms previous state-of-the-art baselines by a large margin. In addition, the effectiveness of our framework can successfully transfer to the few-shot setting, enhancing LMMs on a scale of 10B parameters to be competitive or outperform much larger language models such as ChatGPT and GPT-4. Our MQA framework can serve as a general principle of utilizing LMMs to better solve MIE and potentially other downstream multimodal tasks.

cs.CL↗
arXiv2023

Decomposed Human Motion Prior for Video Pose Estimation via Adversarial Training

Estimating human pose from video is a task that receives considerable attention due to its applicability in numerous 3D fields. The complexity of prior knowledge of human body movements poses a challenge to neural network models in the task of regressing keypoints. In this paper, we address this problem by incorporating motion prior in an adversarial way. Different from previous methods, we propose to decompose holistic motion prior to joint motion prior, making it easier for neural networks to learn from prior knowledge thereby boosting the performance on the task. We also utilize a novel regularization loss to balance accuracy and smoothness introduced by motion prior. Our method achieves 9\% lower PA-MPJPE and 29\% lower acceleration error than previous methods tested on 3DPW. The estimator proves its robustness by achieving impressive performance on in-the-wild dataset.

cs.CV↗
arXiv2023

Designs and Implementations in Neural Network-based Video Coding

The past decade has witnessed the huge success of deep learning in well-known artificial intelligence applications such as face recognition, autonomous driving, and large language model like ChatGPT. Recently, the application of deep learning has been extended to a much wider range, with neural network-based video coding being one of them. Neural network-based video coding can be performed at two different levels: embedding neural network-based (NN-based) coding tools into a classical video compression framework or building the entire compression framework upon neural networks. This paper elaborates some of the recent exploration efforts of JVET (Joint Video Experts Team of ITU-T SG 16 WP 3 and ISO/IEC JTC 1/SC29) in the name of neural network-based video coding (NNVC), falling in the former category. Specifically, this paper discusses two major NN-based video coding technologies, i.e. neural network-based intra prediction and neural network-based in-loop filtering, which have been investigated for several meeting cycles in JVET and finally adopted into the reference software of NNVC. Extensive experiments on top of the NNVC have been conducted to evaluate the effectiveness of the proposed techniques. Compared with VTM-11.0_nnvc, the proposed NN-based coding tools in NNVC-4.0 could achieve {11.94%, 21.86%, 22.59%}, {9.18%, 19.76%, 20.92%}, and {10.63%, 21.56%, 23.02%} BD-rate reductions on average for {Y, Cb, Cr} under random-access, low-delay, and all-intra configurations respectively.

eess.IV↗
arXiv2023

Ray Conditioning: Trading Photo-consistency for Photo-realism in Multi-view Image Generation

Multi-view image generation attracts particular attention these days due to its promising 3D-related applications, e.g., image viewpoint editing. Most existing methods follow a paradigm where a 3D representation is first synthesized, and then rendered into 2D images to ensure photo-consistency across viewpoints. However, such explicit bias for photo-consistency sacrifices photo-realism, causing geometry artifacts and loss of fine-scale details when these methods are applied to edit real images. To address this issue, we propose ray conditioning, a geometry-free alternative that relaxes the photo-consistency constraint. Our method generates multi-view images by conditioning a 2D GAN on a light field prior. With explicit viewpoint control, state-of-the-art photo-realism and identity consistency, our method is particularly suited for the viewpoint editing task.

cs.CV↗
arXiv2023

An optimization framework for wind farm layout design using CFD-based Kriging model

Wind farm layout optimization (WFLO) seeks to alleviate the wake loss and maximize wind farm power output efficiency, and is a crucial process in the design of wind energy projects.Since the optimization algorithms typically require thousands of numerical evaluations of the wake effects, conventional WFLO studies are usually carried out with the low-fidelity analytical wake models.In this paper, we develop an optimization framework for wind farm layout design using CFD-based Kriging model to maximize the annual energy production (AEP) of wind farms. This surrogate-based optimization (SBO) framework uses latin hypercube sampling to generate a group of wind farm layout samples, based on which CFD simulations are carried out to obtain the corresponding AEPs.This wind farm layout dataset is used to train the Kriging model, which is then integrated with an optimizer based on genetic algorithm (GA). As the optimization progresses, the intermediate optimal layout designs are again fed into the dataset.Such adaptive update of wind farm layout dataset continues until the algorithm converges.To evaluate the performance of the proposed SBO framework, we apply it to three representative wind farm cases.Compared to the conventional staggered layout, the optimized wind farm produces significantly higher total AEP.In particular, the SBO framework requires significantly smaller number of CFD calls to yield the optimal layouts that generates almost the same AEP with the direct CFD-GA method.Further analysis on the velocity fields show that the optimization framework attempts to locate the downstream turbines away from the the wakes of upstream ones.The proposed CFD-based surrogate model provides a more accurate and flexible alternative to the conventional analytical-wake-model-based methods in WFLO tasks, and has the potential to be used for designing efficient wind farm projects.

physics.flu-dyn↗
arXiv2023

DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion

Multi-modality image fusion aims to combine different modalities to produce fused images that retain the complementary features of each modality, such as functional highlights and texture details. To leverage strong generative priors and address challenges such as unstable training and lack of interpretability for GAN-based generative methods, we propose a novel fusion algorithm based on the denoising diffusion probabilistic model (DDPM). The fusion task is formulated as a conditional generation problem under the DDPM sampling framework, which is further divided into an unconditional generation subproblem and a maximum likelihood subproblem. The latter is modeled in a hierarchical Bayesian manner with latent variables and inferred by the expectation-maximization (EM) algorithm. By integrating the inference solution into the diffusion sampling iteration, our method can generate high-quality fused images with natural image generative priors and cross-modality information from source images. Note that all we required is an unconditional pre-trained generative model, and no fine-tuning is needed. Our extensive experiments indicate that our approach yields promising fusion results in infrared-visible image fusion and medical image fusion. The code is available at \url{https://github.com/Zhaozixiang1228/MMIF-DDFM}.

cs.CV↗
arXiv2023

Inverse problems for nonlinear progressive waves

We propose and study several inverse problems associated with the nonlinear progressive waves that arise in infrasonic inversions. The nonlinear progressive equation (NPE) is of a quasilinear form $\partial_t^2 u=Δf(x, u)$ with $f(x, u)=c_1(x) u+c_2(x) u^n$, $n\geq 2$, and can be derived from the hyperbolic system of conservation laws associated with the Euler equations. We establish unique identifiability results in determining $f(x, u)$ as well as the associated initial data by the boundary measurement. Our analysis relies on high-order linearisation and construction of proper Gaussian beam solutions for the underlying wave equations. In addition to its theoretical interest, we connect our study to applications of practical importance in infrasound waveform inversion.

math.AP↗
arXiv2023

AdaMCT: Adaptive Mixture of CNN-Transformer for Sequential Recommendation

Sequential recommendation (SR) aims to model users dynamic preferences from a series of interactions. A pivotal challenge in user modeling for SR lies in the inherent variability of user preferences. An effective SR model is expected to capture both the long-term and short-term preferences exhibited by users, wherein the former can offer a comprehensive understanding of stable interests that impact the latter. To more effectively capture such information, we incorporate locality inductive bias into the Transformer by amalgamating its global attention mechanism with a local convolutional filter, and adaptively ascertain the mixing importance on a personalized basis through layer-aware adaptive mixture units, termed as AdaMCT. Moreover, as users may repeatedly browse potential purchases, it is expected to consider multiple relevant items concurrently in long-/short-term preferences modeling. Given that softmax-based attention may promote unimodal activation, we propose the Squeeze-Excitation Attention (with sigmoid activation) into SR models to capture multiple pertinent items (keys) simultaneously. Extensive experiments on three widely employed benchmarks substantiate the effectiveness and efficiency of our proposed approach. Source code is available at https://github.com/juyongjiang/AdaMCT.

cs.IR↗
arXiv2023

Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting

Traffic forecasting is an essential problem in urban planning and computing. The complex dynamic spatial-temporal dependencies among traffic objects (e.g., sensors and road segments) have been calling for highly flexible models; unfortunately, sophisticated models may suffer from poor robustness especially in capturing the trend of the time series (1st-order derivatives with time), leading to unrealistic forecasts. To address the challenge of balancing dynamics and robustness, we propose TrendGCN, a new scheme that extends the flexibility of GCNs and the distribution-preserving capacity of generative and adversarial loss for handling sequential data with inherent statistical correlations. On the one hand, our model simultaneously incorporates spatial (node-wise) embeddings and temporal (time-wise) embeddings to account for heterogeneous space-and-time convolutions; on the other hand, it uses GAN structure to systematically evaluate statistical consistencies between the real and the predicted time series in terms of both the temporal trending and the complex spatial-temporal dependencies. Compared with traditional approaches that handle step-wise predictive errors independently, our approach can produce more realistic and robust forecasts. Experiments on six benchmark traffic forecasting datasets and theoretical analysis both demonstrate the superiority and the state-of-the-art performance of TrendGCN. Source code is available at https://github.com/juyongjiang/TrendGCN.

cs.LG↗
arXiv2023

Boundary Lipschitz Regularity and the Hopf Lemma for Fully Nonlinear Elliptic Equations

In this paper, we study the boundary regularity for viscosity solutions of fully nonlinear elliptic equations. We use a unified, simple method to prove that if the domain $Ω$ satisfies the exterior $C^{1,\mathrm{Dini}}$ condition at $x_0\in \partial Ω$ (see Definition 1.2), the solution is Lipschitz continuous at $x_0$; if $Ω$ satisfies the interior $C^{1,\mathrm{Dini}}$ condition at $x_0$ (see Definition 1.3), the Hopf lemma holds at $x_0$. The key idea is that the curved boundaries are regarded as perturbations of a hyperplane. Moreover, we show that the $C^{1,\mathrm{Dini}}$ conditions are optimal.

math.AP↗
arXiv2023

NTIRE 2023 Quality Assessment of Video Enhancement Challenge

This paper reports on the NTIRE 2023 Quality Assessment of Video Enhancement Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2023. This challenge is to address a major challenge in the field of video processing, namely, video quality assessment (VQA) for enhanced videos. The challenge uses the VQA Dataset for Perceptual Video Enhancement (VDPVE), which has a total of 1211 enhanced videos, including 600 videos with color, brightness, and contrast enhancements, 310 videos with deblurring, and 301 deshaked videos. The challenge has a total of 167 registered participants. 61 participating teams submitted their prediction results during the development phase, with a total of 3168 submissions. A total of 176 submissions were submitted by 37 participating teams during the final testing phase. Finally, 19 participating teams submitted their models and fact sheets, and detailed the methods they used. Some methods have achieved better results than baseline methods, and the winning methods have demonstrated superior prediction performance.

cs.CV↗
arXiv2023

Video Super-Resolution Transformer

Video super-resolution (VSR), with the aim to restore a high-resolution video from its corresponding low-resolution version, is a spatial-temporal sequence prediction problem. Recently, Transformer has been gaining popularity due to its parallel computing ability for sequence-to-sequence modeling. Thus, it seems to be straightforward to apply the vision Transformer to solve VSR. However, the typical block design of Transformer with a fully connected self-attention layer and a token-wise feed-forward layer does not fit well for VSR due to the following two reasons. First, the fully connected self-attention layer neglects to exploit the data locality because this layer relies on linear layers to compute attention maps. Second, the token-wise feed-forward layer lacks the feature alignment which is important for VSR since this layer independently processes each of the input token embeddings without any interaction among them. In this paper, we make the first attempt to adapt Transformer for VSR. Specifically, to tackle the first issue, we present a spatial-temporal convolutional self-attention layer with a theoretical understanding to exploit the locality information. For the second issue, we design a bidirectional optical flow-based feed-forward layer to discover the correlations across different video frames and also align features. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our proposed method. The code will be available at https://github.com/caojiezhang/VSR-Transformer.

cs.CV↗
arXiv2023

High-precision and low-latency widefield diamond quantum sensing with neuromorphic vision sensors

During the past decade, interest has grown significantly in developing ultrasensitive widefield diamond magnetometry for various applications. Despite attempts to improve the adoption of conventional frame-based sensors, achieving high temporal resolution and sensitivity simultaneously remains a key challenge. This is largely due to the transfer and processing of massive amounts of sensor data to capture the widefield fluorescence intensity changes of spin defects in diamonds. In this study, we adopt a neuromorphic vision sensor to address this issue. This sensor pre-processes the detected signals in optically detected magnetic resonance (ODMR) measurements for quantum sensing, employing a working principle that closely resembles the operation of the human vision system. By encoding the changes of light intensity into spikes, this approach results in a vast dynamic range, high temporal resolution, and exceptional signal-to-background ratio. After a thorough evaluation of theoretical feasibility, our experiment with an off-the-shelf event camera demonstrated a 13x improvement in temporal resolution with comparable precision of detecting ODMR resonance frequencies compared with the state-of-the-art highly specialized frame-based approach. A specialized camera system with the same mechanism has the potential to enhance these benefits further. This performance improvement is primarily attributable to orders of magnitude smaller data volumes and, thus, reduced latency. We further showcase the deployment of this technology in monitoring dynamically modulated laser heating of gold nanoparticles coated on a diamond surface, a recognizably difficult task using existing approaches. The current development provides new insights for high-precision and low-latency widefield quantum sensing, with possibilities for integration with emerging memory devices for more efficient event-based data processing.

physics.ins-det↗
arXiv2023

ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge

The primary aim of this research was to address the limitations observed in the medical knowledge of prevalent large language models (LLMs) such as ChatGPT, by creating a specialized language model with enhanced accuracy in medical advice. We achieved this by adapting and refining the large language model meta-AI (LLaMA) using a large dataset of 100,000 patient-doctor dialogues sourced from a widely used online medical consultation platform. These conversations were cleaned and anonymized to respect privacy concerns. In addition to the model refinement, we incorporated a self-directed information retrieval mechanism, allowing the model to access and utilize real-time information from online sources like Wikipedia and data from curated offline medical databases. The fine-tuning of the model with real-world patient-doctor interactions significantly improved the model's ability to understand patient needs and provide informed advice. By equipping the model with self-directed information retrieval from reliable online and offline sources, we observed substantial improvements in the accuracy of its responses. Our proposed ChatDoctor, represents a significant advancement in medical LLMs, demonstrating a significant improvement in understanding patient inquiries and providing accurate advice. Given the high stakes and low error tolerance in the medical field, such enhancements in providing accurate and reliable information are not only beneficial but essential.

cs.CL↗
arXiv2023

Point-Gap Bound States in Non-Hermitian Systems

In this paper, we systematically investigate the impurity-induced bound states in 1D non-Hermitian systems. By establishing an exact relationship between impurity potential and bound-state energy, we determine the minimum impurity potential required to generate bound states within each point energy gap. We demonstrate that the absence of Bloch saddle points necessitates a finite threshold of impurity potential; otherwise, infinitesimal impurity potential can create bound states. Furthermore, we show that the bound states residing in the point gaps with nonzero spectral winding exhibit sensitivity to boundary conditions and will be squeezed towards the edges when the boundaries are opened, indicating the bulk-boundary correspondence in terms of point-gap topology.

cond-mat.mes-hall↗