arXiv subjects

Guang Yang

Publications and source records attributed to Guang Yang.

At least 289 records · Page 16Linked to original sources

arXiv2024

SegmentAnything helps microscopy images based automatic and quantitative organoid detection and analysis

Organoids are self-organized 3D cell clusters that closely mimic the architecture and function of in vivo tissues and organs. Quantification of organoid morphology helps in studying organ development, drug discovery, and toxicity assessment. Recent microscopy techniques provide a potent tool to acquire organoid morphology features, but manual image analysis remains a labor and time-intensive process. Thus, this paper proposes a comprehensive pipeline for microscopy analysis that leverages the SegmentAnything to precisely demarcate individual organoids. Additionally, we introduce a set of morphological properties, including perimeter, area, radius, non-smoothness, and non-circularity, allowing researchers to analyze the organoid structures quantitatively and automatically. To validate the effectiveness of our approach, we conducted tests on bright-field images of human induced pluripotent stem cells (iPSCs) derived neural-epithelial (NE) organoids. The results obtained from our automatic pipeline closely align with manual organoid detection and measurement, showcasing the capability of our proposed method in accelerating organoids morphology analysis.

eess.IV↗

arXiv2024

The Missing U for Efficient Diffusion Models

Diffusion Probabilistic Models stand as a critical tool in generative modelling, enabling the generation of complex data distributions. This family of generative models yields record-breaking performance in tasks such as image synthesis, video generation, and molecule design. Despite their capabilities, their efficiency, especially in the reverse process, remains a challenge due to slow convergence rates and high computational costs. In this paper, we introduce an approach that leverages continuous dynamical systems to design a novel denoising network for diffusion models that is more parameter-efficient, exhibits faster convergence, and demonstrates increased noise robustness. Experimenting with Denoising Diffusion Probabilistic Models (DDPMs), our framework operates with approximately a quarter of the parameters, and $\sim$ 30\% of the Floating Point Operations (FLOPs) compared to standard U-Nets in DDPMs. Furthermore, our model is notably faster in inference than the baseline when measured in fair and equal conditions. We also provide a mathematical intuition as to why our proposed reverse process is faster as well as a mathematical discussion of the empirical tradeoffs in the denoising downstream task. Finally, we argue that our method is compatible with existing performance enhancement techniques, enabling further improvements in efficiency, quality, and speed.

cs.LG↗

arXiv2024

Mapping the Growth of Supermassive Black Holes as a Function of Galaxy Stellar Mass and Redshift

The growth of supermassive black holes is strongly linked to their galaxies. It has been shown that the population mean black-hole accretion rate ($\overline{\mathrm{BHAR}}$) primarily correlates with the galaxy stellar mass ($M_\star$) and redshift for the general galaxy population. This work aims to provide the best measurements of $\overline{\mathrm{BHAR}}$ as a function of $M_\star$ and redshift over ranges of $10^{9.5}<M_\star<10^{12}~M_\odot$ and $z<4$. We compile an unprecedentedly large sample with eight thousand active galactic nuclei (AGNs) and 1.3 million normal galaxies from nine high-quality survey fields following a wedding-cake design. We further develop a semiparametric Bayesian method that can reasonably estimate $\overline{\mathrm{BHAR}}$ and the corresponding uncertainties, even for sparsely populated regions in the parameter space. $\overline{\mathrm{BHAR}}$ is constrained by X-ray surveys sampling the AGN accretion power and UV-to-infrared multi-wavelength surveys sampling the galaxy population. Our results can independently predict the X-ray luminosity function (XLF) from the galaxy stellar mass function (SMF), and the prediction is consistent with the observed XLF. We also try adding external constraints from the observed SMF and XLF. We further measure $\overline{\mathrm{BHAR}}$ for star-forming and quiescent galaxies and show that star-forming $\overline{\mathrm{BHAR}}$ is generally larger than or at least comparable to the quiescent $\overline{\mathrm{BHAR}}$.

astro-ph.GA↗

arXiv2024

ContrastDiagnosis: Enhancing Interpretability in Lung Nodule Diagnosis Using Contrastive Learning

With the ongoing development of deep learning, an increasing number of AI models have surpassed the performance levels of human clinical practitioners. However, the prevalence of AI diagnostic products in actual clinical practice remains significantly lower than desired. One crucial reason for this gap is the so-called `black box' nature of AI models. Clinicians' distrust of black box models has directly hindered the clinical deployment of AI products. To address this challenge, we propose ContrastDiagnosis, a straightforward yet effective interpretable diagnosis framework. This framework is designed to introduce inherent transparency and provide extensive post-hoc explainability for deep learning model, making them more suitable for clinical medical diagnosis. ContrastDiagnosis incorporates a contrastive learning mechanism to provide a case-based reasoning diagnostic rationale, enhancing the model's transparency and also offers post-hoc interpretability by highlighting similar areas. High diagnostic accuracy was achieved with AUC of 0.977 while maintain a high transparency and explainability.

cs.CV↗

arXiv2024

Automatic Bi-modal Question Title Generation for Stack Overflow with Prompt Learning

When drafting question posts for Stack Overflow, developers may not accurately summarize the core problems in the question titles, which can cause these questions to not get timely help. Therefore, improving the quality of question titles has attracted the wide attention of researchers. An initial study aimed to automatically generate the titles by only analyzing the code snippets in the question body. However, this study ignored the helpful information in their corresponding problem descriptions. Therefore, we propose an approach SOTitle+ by considering bi-modal information (i.e., the code snippets and the problem descriptions) in the question body. Then we formalize the title generation for different programming languages as separate but related tasks and utilize multi-task learning to solve these tasks. Later we fine-tune the pre-trained language model CodeT5 to automatically generate the titles. Unfortunately, the inconsistent inputs and optimization objectives between the pre-training task and our investigated task may make fine-tuning hard to fully explore the knowledge of the pre-trained model. To solve this issue, SOTitle+ further prompt-tunes CodeT5 with hybrid prompts (i.e., mixture of hard and soft prompts). To verify the effectiveness of SOTitle+, we construct a large-scale high-quality corpus from recent data dumps shared by Stack Overflow. Our corpus includes 179,119 high-quality question posts for six popular programming languages. Experimental results show that SOTitle+ can significantly outperform four state-of-the-art baselines in both automatic evaluation and human evaluation. Our work indicates that considering bi-modal information and prompt learning in Stack Overflow title generation is a promising exploration direction.

cs.SE↗

arXiv2024

One for Multiple: Physics-informed Synthetic Data Boosts Generalizable Deep Learning for Fast MRI Reconstruction

Magnetic resonance imaging (MRI) is a widely used radiological modality renowned for its radiation-free, comprehensive insights into the human body, facilitating medical diagnoses. However, the drawback of prolonged scan times hinders its accessibility. The k-space undersampling offers a solution, yet the resultant artifacts necessitate meticulous removal during image reconstruction. Although Deep Learning (DL) has proven effective for fast MRI image reconstruction, its broader applicability across various imaging scenarios has been constrained. Challenges include the high cost and privacy restrictions associated with acquiring large-scale, diverse training data, coupled with the inherent difficulty of addressing mismatches between training and target data in existing DL methodologies. Here, we present a novel Physics-Informed Synthetic data learning framework for Fast MRI, called PISF. PISF marks a breakthrough by enabling generalized DL for multi-scenario MRI reconstruction through a single trained model. Our approach separates the reconstruction of a 2D image into many 1D basic problems, commencing with 1D data synthesis to facilitate generalization. We demonstrate that training DL models on synthetic data, coupled with enhanced learning techniques, yields in vivo MRI reconstructions comparable to or surpassing those of models trained on matched realistic datasets, reducing the reliance on real-world MRI data by up to 96%. Additionally, PISF exhibits remarkable generalizability across multiple vendors and imaging centers. Its adaptability to diverse patient populations has been validated through evaluations by ten experienced medical professionals. PISF presents a feasible and cost-effective way to significantly boost the widespread adoption of DL in various fast MRI applications.

eess.IV↗

arXiv2024

Make it more specific: A novel uncertainty based airway segmentation application on 3D U-Net and its variants

Each medical segmentation task should be considered with a specific AI algorithm based on its scenario so that the most accurate prediction model can be obtained. The most popular algorithms in medical segmentation, 3D U-Net and its variants, can directly implement the task of lung trachea segmentation, but its failure to consider the special tree-like structure of the trachea suggests that there is much room for improvement in its segmentation accuracy. Therefore, a research gap exists because a great amount of state-of-the-art DL algorithms are vanilla 3D U-Net structures, which do not introduce the various performance-enhancing modules that come with special natural image modality in lung airway segmentation. In this paper, we proposed two different network structures Branch-Level U-Net (B-UNet) and Branch-Level CE-UNet (B-CE-UNet) which are based on U-Net structure and compared the prediction results with the same dataset. Specially, both of the two networks add branch loss and central line loss to learn the feature of fine branch endings of the airways. Uncertainty estimation algorithms are also included to attain confident predictions and thereby, increase the overall trustworthiness of our whole model. In addition, predictions of the lung trachea based on the maximum connectivity rate were calculated and extracted during post-processing for segmentation refinement and pruning.

cs.CV↗

arXiv2024

Investigating the Star Formation Rates of AGN Hosts Relative to the Star-Forming Main Sequence

A fundamental question in galaxy and black-hole evolution remains how galaxies and their supermassive black holes have evolved together over cosmic time. Specifically, it is still unclear how the position of X-ray active galactic nucleus (AGN) host galaxies with respect to the star-forming main sequence (MS) may change with the X-ray luminosity ($L_\mathrm{X}$) of the AGN or the stellar mass ($M_\star$) of the host galaxy. We use data from XMM-SERVS to probe this issue. XMM-SERVS is covered by the largest medium-depth X-ray survey (with superb supporting multiwavelength data) and thus contains the largest sample to date for study. To ensure consistency, we locally derive the MS from a large reference galaxy sample. In our analysis, we demonstrate that the turnover of the galaxy MS does not allow reliable conclusions to be drawn for high-mass AGNs, and we establish a robust safe regime where the results do not depend upon the choice of MS definition. Under this framework, our results indicate that less-massive AGN host-galaxies ($\log M_\star\sim9.5-10.5$ $M_\odot$) generally possess enhanced SFRs compared to their normal-galaxy counterparts while the more-massive AGN host galaxies ($\log M_\star\sim10.5-11.5$ $M_\odot$) lie on or below the star-forming MS. Further, we propose an empirical model for how the placement of an AGN with respect to the MS (SFR$_{norm}$) evolves as a function of both $M_\star$ and $L_\mathrm{X}$.

astro-ph.GA↗

arXiv2024

Machine-Learned Atomic Cluster Expansion Potentials for Fast and Quantum-Accurate Thermal Simulations of Wurtzite AlN

Using the atomic cluster expansion (ACE) framework, we develop a machine learning interatomic potential for fast and accurately modelling the phonon transport properties of wurtzite aluminum nitride. The predictive power of the ACE potential against density functional theory (DFT) is demonstrated across a broad range of properties of w-AlN, including ground-state lattice parameters, specific heat capacity, coefficients of thermal expansion, bulk modulus, and harmonic phonon dispersions. Validation of lattice thermal conductivity is further carried out by comparing the ACE-predicted values to the DFT calculations and experiments, exhibiting the overall capability of our ACE potential in sufficiently describing anharmonic phonon interactions. As a practical application, we perform a lattice dynamics analysis using the potential to unravel the effects of biaxial strains on thermal conductivity and phonon properties of w-AlN, which is identified as a significant tuning factor for near-junction thermal design of w-AlN-based electronics.

cond-mat.mtrl-sci↗

arXiv2024

Automatic Smart Contract Comment Generation via Large Language Models and In-Context Learning

The previous smart contract code comment (SCC) generation approaches can be divided into two categories: fine-tuning paradigm-based approaches and information retrieval-based approaches. However, for the fine-tuning paradigm-based approaches, the performance may be limited by the quality of the gathered dataset for the downstream task and they may have knowledge-forgetting issues. While for the information retrieval-based approaches, it is difficult for them to generate high-quality comments if similar code does not exist in the historical repository. Therefore we want to utilize the domain knowledge related to SCC generation in large language models (LLMs) to alleviate the disadvantages of these two types of approaches. In this study, we propose an approach SCCLLM based on LLMs and in-context learning. Specifically, in the demonstration selection phase, SCCLLM retrieves the top-k code snippets from the historical corpus by considering syntax, semantics, and lexical information. In the in-context learning phase, SCCLLM utilizes the retrieved code snippets as demonstrations, which can help to utilize the related knowledge for this task. We select a large corpus from a smart contract community Etherscan.io as our experimental subject. Extensive experimental results show the effectiveness of SCCLLM when compared with baselines in automatic evaluation and human evaluation.

cs.SE↗

arXiv2024

Galaxies Going Bananas: Inferring the 3D Geometry of High-Redshift Galaxies with JWST-CEERS

The 3D geometry of high-redshift galaxies remains poorly understood. We build a differentiable Bayesian model and use Hamiltonian Monte Carlo to efficiently and robustly infer the 3D shapes of star-forming galaxies in JWST-CEERS observations with $\log M_*/M_{\odot}=9.0-10.5$ at $z=0.5-8.0$. We reproduce previous results from HST-CANDELS in a fraction of the computing time and constrain the mean ellipticity, triaxiality, size and covariances with samples as small as $\sim50$ galaxies. We find high 3D ellipticities for all mass-redshift bins suggesting oblate (disky) or prolate (elongated) geometries. We break that degeneracy by constraining the mean triaxiality to be $\sim1$ for $\log M_*/M_{\odot}=9.0-9.5$ dwarfs at $z>1$ (favoring the prolate scenario), with significantly lower triaxialities for higher masses and lower redshifts indicating the emergence of disks. The prolate population traces out a ``banana'' in the projected $b/a-\log a$ diagram with an excess of low $b/a$, large $\log a$ galaxies. The dwarf prolate fraction rises from $\sim25\%$ at $z=0.5-1.0$ to $\sim50-80\%$ at $z=3-8$. If these are disks, they cannot be axisymmetric but instead must be unusually oval (triaxial) unlike local circular disks. We simultaneously constrain the 3D size-mass relation and its dependence on 3D geometry. High-probability prolate and oblate candidates show remarkably similar Sérsic indices ($n\sim1$), non-parametric morphological properties and specific star formation rates. Both tend to be visually classified as disks or irregular but edge-on oblate candidates show more dust attenuation. We discuss selection effects, follow-up prospects and theoretical implications.

astro-ph.GA↗

arXiv2023

Reducing Spatial Fitting Error in Distillation of Denoising Diffusion Models

Denoising Diffusion models have exhibited remarkable capabilities in image generation. However, generating high-quality samples requires a large number of iterations. Knowledge distillation for diffusion models is an effective method to address this limitation with a shortened sampling process but causes degraded generative quality. Based on our analysis with bias-variance decomposition and experimental observations, we attribute the degradation to the spatial fitting error occurring in the training of both the teacher and student model. Accordingly, we propose $\textbf{S}$patial $\textbf{F}$itting-$\textbf{E}$rror $\textbf{R}$eduction $\textbf{D}$istillation model ($\textbf{SFERD}$). SFERD utilizes attention guidance from the teacher model and a designed semantic gradient predictor to reduce the student's fitting error. Empirically, our proposed model facilitates high-quality sample generation in a few function evaluations. We achieve an FID of 5.31 on CIFAR-10 and 9.39 on ImageNet 64$\times$64 with only one step, outperforming existing diffusion methods. Our study provides a new perspective on diffusion distillation by highlighting the intrinsic denoising ability of models. Project link: \url{https://github.com/Sainzerjj/SFERD}.

cs.CV↗

arXiv2023

A Dual Domain Multi-exposure Image Fusion Network based on the Spatial-Frequency Integration

Multi-exposure image fusion aims to generate a single high-dynamic image by integrating images with different exposures. Existing deep learning-based multi-exposure image fusion methods primarily focus on spatial domain fusion, neglecting the global modeling ability of the frequency domain. To effectively leverage the global illumination modeling ability of the frequency domain, we propose a novelty perspective on multi-exposure image fusion via the Spatial-Frequency Integration Framework, named MEF-SFI. Initially, we revisit the properties of the Fourier transform on the 2D image, and verify the feasibility of multi-exposure image fusion on the frequency domain where the amplitude and phase component is able to guide the integration of the illumination information. Subsequently, we present the deep Fourier-based multi-exposure image fusion framework, which consists of a spatial path and frequency path for local and global modeling separately. Specifically, we introduce a Spatial-Frequency Fusion Block to facilitate efficient interaction between dual domains and capture complementary information from input images with different exposures. Finally, we combine a dual domain loss function to ensure the retention of complementary information in both the spatial and frequency domains. Extensive experiments on the PQA-MEF dataset demonstrate that our method achieves visual-appealing fusion results against state-of-the-art multi-exposure image fusion approaches. Our code is available at https://github.com/SSyangguang/MEF-freq.

cs.CV↗

arXiv2023

The Stochastic Schwarz lemma on Kähler Manifolds by Couplings and Its Applications

We first provide a stochastic formula for the Carathéodory distance in terms of general Markovian couplings and prove a comparison result between the Carathéodory distance and the complete Kähler metric with a negative lower curvature bound using the Kendall-Cranston coupling. This probabilistic approach gives a version of the Schwarz lemma on complete non-compact Kähler manifolds with a further decomposition Ricci curvature into the orthogonal Ricci curvature and the holomorphic sectional curvature, which cannot be obtained by using Yau--Royden's Schwarz lemma. We also prove coupling estimates on quaternionic Kähler manifolds. As a byproduct, we obtain an improved gradient estimate of positive harmonic functions on Kähler manifolds and quaternionic Kähler manifolds under lower curvature bounds.

math.DG↗

arXiv2023

Where to Begin? From Random to Foundation Model Instructed Initialization in Federated Learning for Medical Image Segmentation

In medical image analysis, Federated Learning (FL) stands out as a key technology that enables privacy-preserved, decentralized data processing, crucial for handling sensitive medical data. Currently, most FL models employ random initialization, which has been proven effective in various instances. However, given the unique challenges posed by non-IID (independently and identically distributed) data in FL, we propose a novel perspective: exploring the impact of using the foundation model with enormous pre-trained knowledge, such as the Segment Anything Model (SAM), as an instructive teacher for FL model initialization in medical image segmentation task. This work for the first time attempts to utilize the foundation model as an instructive teacher for initialization in FL, assessing its impact on the performance of FL models, especially in non-IID data scenarios. Our empirical evaluation on chest x-ray lung segmentation showcases that FL with foundation model instructed initialization not only achieves faster convergence but also improves performance in complex data contexts. These findings offer a new perspective for model initialization in FL.

cs.CV↗

arXiv2023

Dynamic Multimodal Information Bottleneck for Multimodality Classification

Effectively leveraging multimodal data such as various images, laboratory tests and clinical information is gaining traction in a variety of AI-based medical diagnosis and prognosis tasks. Most existing multi-modal techniques only focus on enhancing their performance by leveraging the differences or shared features from various modalities and fusing feature across different modalities. These approaches are generally not optimal for clinical settings, which pose the additional challenges of limited training data, as well as being rife with redundant data or noisy modality channels, leading to subpar performance. To address this gap, we study the robustness of existing methods to data redundancy and noise and propose a generalized dynamic multimodal information bottleneck framework for attaining a robust fused feature representation. Specifically, our information bottleneck module serves to filter out the task-irrelevant information and noises in the fused feature, and we further introduce a sufficiency loss to prevent dropping of task-relevant information, thus explicitly preserving the sufficiency of prediction information in the distilled feature. We validate our model on an in-house and a public COVID19 dataset for mortality prediction as well as two public biomedical datasets for diagnostic tasks. Extensive experiments show that our method surpasses the state-of-the-art and is significantly more robust, being the only method to remain performance when large-scale noisy channels exist. Our code is publicly available at https://github.com/ayanglab/DMIB.

eess.IV↗

arXiv2023

Post-COVID Highlights: Challenges and Solutions of AI Techniques for Swift Identification of COVID-19

Since the onset of the COVID-19 pandemic in 2019, there has been a concerted effort to develop cost-effective, non-invasive, and rapid AI-based tools. These tools were intended to alleviate the burden on healthcare systems, control the rapid spread of the virus, and enhance intervention outcomes, all in response to this unprecedented global crisis. As we transition into a post-COVID era, we retrospectively evaluate these proposed studies and offer a review of the techniques employed in AI diagnostic models, with a focus on the solutions proposed for different challenges. This review endeavors to provide insights into the diverse solutions designed to address the multifaceted challenges that arose during the pandemic. By doing so, we aim to prepare the AI community for the development of AI tools tailored to address public health emergencies effectively.

cs.CY↗

arXiv2023

Evidence for a Shallow Evolution in the Volume Densities of Massive Galaxies at $z=4$ to $8$ from CEERS

We analyze the evolution of massive (log$_{10}$ [$M_\star/M_\odot$] $>10$) galaxies at $z \sim$ 4--8 selected from the JWST Cosmic Evolution Early Release Science (CEERS) survey. We infer the physical properties of all galaxies in the CEERS NIRCam imaging through spectral energy distribution (SED) fitting with dense basis to select a sample of high redshift massive galaxies. Where available we include constraints from additional CEERS observing modes, including 18 sources with MIRI photometric coverage, and 28 sources with spectroscopic confirmations from NIRSpec or NIRCam wide-field slitless spectroscopy. We sample the recovered posteriors in stellar mass from SED fitting to infer the volume densities of massive galaxies across cosmic time, taking into consideration the potential for sample contamination by active galactic nuclei (AGN). We find that the evolving abundance of massive galaxies tracks expectations based on a constant baryon conversion efficiency in dark matter halos for $z \sim$ 1--4. At higher redshifts, we observe an excess abundance of massive galaxies relative to this simple model. These higher abundances can be explained by modest changes to star formation physics and/or the efficiencies with which star formation occurs in massive dark matter halos, and are not in tension with modern cosmology.

astro-ph.GA↗