arXiv subjects

Hao Wei

Publications and source records attributed to Hao Wei.

At least 55 records · Page 3Linked to original sources

arXiv2024

Fast Radio Bursts as Standard Candles for Cosmology

Recently, fast radio bursts (FRBs) have become a thriving field in astronomy and cosmology. Due to their extragalactic and cosmological origin, they are useful to study the cosmic expansion and the intergalactic medium (IGM). In the literature, the dispersion measure (DM) of FRB has been considered extensively. It could be used as an indirect proxy of the luminosity distance $d_L$ of FRB. The observed DM contains the contributions from the Milky Way (MW), the MW halo, IGM, and the host galaxy. Unfortunately, IGM and the host galaxy of FRB are poorly known to date, and hence the large uncertainties of $\rm DM_{IGM}$ and $\rm DM_{host}$ in DM plague the FRB cosmology. Could we avoid DM in studying cosmology? Could we instead consider the luminosity distance $d_L$ directly in the FRB cosmology? We are interested to find a way out for this problem in the present work. From the lessons of calibrating type Ia supernovae (SNIa) or long gamma-ray bursts (GRBs) as standard candles, we consider a universal subclassification scheme for FRBs, and there are some empirical relations for them. In the present work, we propose to calibrate type Ib FRBs as standard candles by using a tight empirical relation without DM. The calibrated type Ib FRBs at high redshifts can be used like SNIa to constrain the cosmological models. We also test the key factors affecting the calibration and the cosmological constraints. Notice that the results are speculative, since they are based on simulations for the future (instead of now). We stress that the point in the present work is just to propose a viable method and a workable pipeline using type Ib FRBs as standard candles for cosmology in the future.

astro-ph.HE↗

arXiv2024

RoomDiffusion: A Specialized Diffusion Model in the Interior Design Industry

Recent advancements in text-to-image diffusion models have significantly transformed visual content generation, yet their application in specialized fields such as interior design remains underexplored. In this paper, we present RoomDiffusion, a pioneering diffusion model meticulously tailored for the interior design industry. To begin with, we build from scratch a whole data pipeline to update and evaluate data for iterative model optimization. Subsequently, techniques such as multiaspect training, multi-stage fine-tune and model fusion are applied to enhance both the visual appeal and precision of the generated results. Lastly, leveraging the latent consistency Distillation method, we distill and expedite the model for optimal efficiency. Unlike existing models optimized for general scenarios, RoomDiffusion addresses specific challenges in interior design, such as lack of fashion, high furniture duplication rate, and inaccurate style. Through our holistic human evaluation protocol with more than 20 professional human evaluators, RoomDiffusion demonstrates industry-leading performance in terms of aesthetics, accuracy, and efficiency, surpassing all existing open source models such as stable diffusion and SDXL.

cs.CV↗

arXiv2024

Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior

Image compression at extremely low bitrates (below 0.1 bits per pixel (bpp)) is a significant challenge due to substantial information loss. In this work, we propose a novel two-stage extreme image compression framework that exploits the powerful generative capability of pre-trained diffusion models to achieve realistic image reconstruction at extremely low bitrates. In the first stage, we treat the latent representation of images in the diffusion space as guidance, employing a VAE-based compression approach to compress images and initially decode the compressed information into content variables. The second stage leverages pre-trained stable diffusion to reconstruct images under the guidance of content variables. Specifically, we introduce a small control module to inject content information while keeping the stable diffusion model fixed to maintain its generative capability. Furthermore, we design a space alignment loss to force the content variables to align with the diffusion space and provide the necessary constraints for optimization. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches in terms of visual performance at extremely low bitrates. The source code and trained models are available at https://github.com/huai-chang/DiffEIC.

eess.IV↗

arXiv2024

MEDCO: Medical Education Copilots Based on A Multi-Agent Framework

Large language models (LLMs) have had a significant impact on diverse research domains, including medicine and healthcare. However, the potential of LLMs as copilots in medical education remains underexplored. Current AI-assisted educational tools are limited by their solitary learning approach and inability to simulate the multi-disciplinary and interactive nature of actual medical training. To address these limitations, we propose MEDCO (Medical EDucation COpilots), a novel multi-agent-based copilot system specially developed to emulate real-world medical training environments. MEDCO incorporates three primary agents: an agentic patient, an expert doctor, and a radiologist, facilitating a multi-modal and interactive learning environment. Our framework emphasizes the learning of proficient question-asking skills, multi-disciplinary collaboration, and peer discussions between students. Our experiments show that simulated virtual students who underwent training with MEDCO not only achieved substantial performance enhancements comparable to those of advanced models, but also demonstrated human-like learning behaviors and improvements, coupled with an increase in the number of learning samples. This work contributes to medical education by introducing a copilot that implements an interactive and collaborative learning approach. It also provides valuable insights into the effectiveness of AI-integrated training paradigms.

cs.AI↗

arXiv2024

RGB Guided ToF Imaging System: A Survey of Deep Learning-based Methods

Integrating an RGB camera into a ToF imaging system has become a significant technique for perceiving the real world. The RGB guided ToF imaging system is crucial to several applications, including face anti-spoofing, saliency detection, and trajectory prediction. Depending on the distance of the working range, the implementation schemes of the RGB guided ToF imaging systems are different. Specifically, ToF sensors with a uniform field of illumination, which can output dense depth but have low resolution, are typically used for close-range measurements. In contrast, LiDARs, which emit laser pulses and can only capture sparse depth, are usually employed for long-range detection. In the two cases, depth quality improvement for RGB guided ToF imaging corresponds to two sub-tasks: guided depth super-resolution and guided depth completion. In light of the recent significant boost to the field provided by deep learning, this paper comprehensively reviews the works related to RGB guided ToF imaging, including network structures, learning strategies, evaluation metrics, benchmark datasets, and objective functions. Besides, we present quantitative comparisons of state-of-the-art methods on widely used benchmark datasets. Finally, we discuss future trends and the challenges in real applications for further research.

cs.CV↗

arXiv2024

Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Survey

This paper introduces a novel benchmark as part of the AIS 2024 Real-Time Image Super-Resolution (RTSR) Challenge, which aims to upscale compressed images from 540p to 4K resolution (4x factor) in real-time on commercial GPUs. For this, we use a diverse test set containing a variety of 4K images ranging from digital art to gaming and photography. The images are compressed using the modern AVIF codec, instead of JPEG. All the proposed methods improve PSNR fidelity over Lanczos interpolation, and process images under 10ms. Out of the 160 participants, 25 teams submitted their code and models. The solutions present novel designs tailored for memory-efficiency and runtime on edge devices. This survey describes the best solutions for real-time SR of compressed high-resolution images.

cs.CV↗

arXiv2024

VisionCLIP: An Med-AIGC based Ethical Language-Image Foundation Model for Generalizable Retina Image Analysis

Generalist foundation model has ushered in newfound capabilities in medical domain. However, the contradiction between the growing demand for high-quality annotated data with patient privacy continues to intensify. The utilization of medical artificial intelligence generated content (Med-AIGC) as an inexhaustible resource repository arises as a potential solution to address the aforementioned challenge. Here we harness 1 million open-source synthetic fundus images paired with natural language descriptions, to curate an ethical language-image foundation model for retina image analysis named VisionCLIP. VisionCLIP achieves competitive performance on three external datasets compared with the existing method pre-trained on real-world data in a zero-shot fashion. The employment of artificially synthetic images alongside corresponding textual data for training enables the medical foundation model to successfully assimilate knowledge of disease symptomatology, thereby circumventing potential breaches of patient confidentiality.

cs.CV↗

arXiv2023

Leveraging Multimodal Fusion for Enhanced Diagnosis of Multiple Retinal Diseases in Ultra-wide OCTA

Ultra-wide optical coherence tomography angiography (UW-OCTA) is an emerging imaging technique that offers significant advantages over traditional OCTA by providing an exceptionally wide scanning range of up to 24 x 20 $mm^{2}$, covering both the anterior and posterior regions of the retina. However, the currently accessible UW-OCTA datasets suffer from limited comprehensive hierarchical information and corresponding disease annotations. To address this limitation, we have curated the pioneering M3OCTA dataset, which is the first multimodal (i.e., multilayer), multi-disease, and widest field-of-view UW-OCTA dataset. Furthermore, the effective utilization of multi-layer ultra-wide ocular vasculature information from UW-OCTA remains underdeveloped. To tackle this challenge, we propose the first cross-modal fusion framework that leverages multi-modal information for diagnosing multiple diseases. Through extensive experiments conducted on our openly available M3OCTA dataset, we demonstrate the effectiveness and superior performance of our method, both in fixed and varying modalities settings. The construction of the M3OCTA dataset, the first multimodal OCTA dataset encompassing multiple diseases, aims to advance research in the ophthalmic image analysis community.

eess.IV↗

arXiv2023

Higher or Lower: Challenges in Object based SLAM

Simultaneous localization and mapping, as a fundamental task in computer vision, has gained higher demands for performance in recent years due to the rapid development of autonomous driving and unmanned aerial vehicles. Traditional SLAM algorithms highly rely on basic geometry features such as points and lines, which are susceptible to environment. Conversely, higher-level object features offer richer information that is crucial for enhancing the overall performance of the framework. However, the effective utilization of object features necessitates careful consideration of various challenges, including complexity and process velocity. Given the advantages and disadvantages of both high-level object feature and low-level geometry features, it becomes essential to make informed choices within the SLAM framework. Taking these factors into account, this paper provides a thorough comparison between geometry features and object features, analyzes the current mainstream application methods of object features in SLAM frameworks, and presents a comprehensive overview of the main challenges involved in object-based SLAM.

cs.RO↗

arXiv2023

VisionFM: a Multi-Modal Multi-Task Vision Foundation Model for Generalist Ophthalmic Artificial Intelligence

We present VisionFM, a foundation model pre-trained with 3.4 million ophthalmic images from 560,457 individuals, covering a broad range of ophthalmic diseases, modalities, imaging devices, and demography. After pre-training, VisionFM provides a foundation to foster multiple ophthalmic artificial intelligence (AI) applications, such as disease screening and diagnosis, disease prognosis, subclassification of disease phenotype, and systemic biomarker and disease prediction, with each application enhanced with expert-level intelligence and accuracy. The generalist intelligence of VisionFM outperformed ophthalmologists with basic and intermediate levels in jointly diagnosing 12 common ophthalmic diseases. Evaluated on a new large-scale ophthalmic disease diagnosis benchmark database, as well as a new large-scale segmentation and detection benchmark database, VisionFM outperformed strong baseline deep neural networks. The ophthalmic image representations learned by VisionFM exhibited noteworthy explainability, and demonstrated strong generalizability to new ophthalmic modalities, disease spectrum, and imaging devices. As a foundation model, VisionFM has a large capacity to learn from diverse ophthalmic imaging data and disparate datasets. To be commensurate with this capacity, in addition to the real data used for pre-training, we also generated and leveraged synthetic ophthalmic imaging data. Experimental results revealed that synthetic data that passed visual Turing tests, can also enhance the representation learning capability of VisionFM, leading to substantial performance gains on downstream ophthalmic AI tasks. Beyond the ophthalmic AI applications developed, validated, and demonstrated in this work, substantial further applications can be achieved in an efficient and cost-effective manner using VisionFM as the foundation.

eess.IV↗

arXiv2023

CauDR: A Causality-inspired Domain Generalization Framework for Fundus-based Diabetic Retinopathy Grading

Diabetic retinopathy (DR) is the most common diabetic complication, which usually leads to retinal damage, vision loss, and even blindness. A computer-aided DR grading system has a significant impact on helping ophthalmologists with rapid screening and diagnosis. Recent advances in fundus photography have precipitated the development of novel retinal imaging cameras and their subsequent implementation in clinical practice. However, most deep learning-based algorithms for DR grading demonstrate limited generalization across domains. This inferior performance stems from variance in imaging protocols and devices inducing domain shifts. We posit that declining model performance between domains arises from learning spurious correlations in the data. Incorporating do-operations from causality analysis into model architectures may mitigate this issue and improve generalizability. Specifically, a novel universal structural causal model (SCM) was proposed to analyze spurious correlations in fundus imaging. Building on this, a causality-inspired diabetic retinopathy grading framework named CauDR was developed to eliminate spurious correlations and achieve more generalizable DR diagnostics. Furthermore, existing datasets were reorganized into 4DR benchmark for DG scenario. Results demonstrate the effectiveness and the state-of-the-art (SOTA) performance of CauDR.

cs.CV↗

arXiv2023

Generalist Vision Foundation Models for Medical Imaging: A Case Study of Segment Anything Model on Zero-Shot Medical Segmentation

In this paper, we examine the recent Segment Anything Model (SAM) on medical images, and report both quantitative and qualitative zero-shot segmentation results on nine medical image segmentation benchmarks, covering various imaging modalities, such as optical coherence tomography (OCT), magnetic resonance imaging (MRI), and computed tomography (CT), as well as different applications including dermatology, ophthalmology, and radiology. Those benchmarks are representative and commonly used in model development. Our experimental results indicate that while SAM presents remarkable segmentation performance on images from the general domain, its zero-shot segmentation ability remains restricted for out-of-distribution images, e.g., medical images. In addition, SAM exhibits inconsistent zero-shot segmentation performance across different unseen medical domains. For certain structured targets, e.g., blood vessels, the zero-shot segmentation of SAM completely failed. In contrast, a simple fine-tuning of it with a small amount of data could lead to remarkable improvement of the segmentation quality, showing the great potential and feasibility of using fine-tuned SAM to achieve accurate medical image segmentation for a precision diagnostics. Our study indicates the versatility of generalist vision foundation models on medical imaging, and their great potential to achieve desired performance through fine-turning and eventually address the challenges associated with accessing large and diverse medical datasets in support of clinical diagnostics.

cs.CV↗

arXiv2022

Rethinking Blur Synthesis for Deep Real-World Image Deblurring

In this paper, we examine the problem of real-world image deblurring and take into account two key factors for improving the performance of the deep image deblurring model, namely, training data synthesis and network architecture design. Deblurring models trained on existing synthetic datasets perform poorly on real blurry images due to domain shift. To reduce the domain gap between synthetic and real domains, we propose a novel realistic blur synthesis pipeline to simulate the camera imaging process. As a result of our proposed synthesis method, existing deblurring models could be made more robust to handle real-world blur. Furthermore, we develop an effective deblurring model that captures non-local dependencies and local context in the feature domain simultaneously. Specifically, we introduce the multi-path transformer module to UNet architecture for enriched multi-scale features learning. A comprehensive experiment on three real-world datasets shows that the proposed deblurring model performs better than state-of-the-art methods.

cs.CV↗

arXiv2022

A Possible Subclassification of Fast Radio Bursts

Although fast radio bursts (FRBs) have been an active field in astronomy and cosmology, their origin is still unknown to date. One of the interesting topics is the classification of FRBs, which is closely related to the origin of FRBs. Different physical mechanisms are required by different classes of FRBs. In the literature, they usually could be classified into non-repeating and repeating FRBs. Well motivated by the observations, here we are interested in the possible subclassification of FRBs. By using the first CHIME/FRB catalog, we propose to subclassify non-repeating (type I) FRBs into type Ia and Ib FRBs. The distribution of type Ia FRBs is delayed with respect to the cosmic star formation history (SFH), and hence they are probably associated with old stellar populations, while the distribution of type Ib FRBs tracks SFH, and hence they are probably associated with young stellar populations. Accordingly, the physical criteria for this subclassification of type I FRBs have been clearly determined. We find that there are some tight empirical correlations for type Ia FRBs but not for type Ib FRBs, and vice versa. These make them different in physical properties. Similarly, we suggest that repeating (type II) FRBs could also be subclassified into type IIa and IIb FRBs. A universal subclassification scheme is given at the end. This subclassification of FRBs might help us to reveal quite different physical mechanisms behind them, and improve their applications in astronomy and cosmology.

astro-ph.HE↗

arXiv2022

Fast Radio Burst Distributions Consistent with the First CHIME/FRB Catalog

Currently, fast radio bursts (FRBs) have become a very active field in astronomy and cosmology. However, the origin of FRBs is still unknown to date. The studies on the intrinsic FRB distributions might help us to reveal the possible origins of FRBs, and improve the simulations for FRB cosmology. Recently, the first CHIME/FRB catalog of 536 events was released. Such a large uniform sample of FRBs detected by a single telescope is very valuable to test the FRB distributions. Later, it has been claimed that the FRB distribution model tracking the cosmic star formation history (SFH) was rejected by the first CHIME/FRB catalog. In the present work, we consider some empirical FRB distribution models, and find that many of them can be fully consistent with the CHIME/FRB observational data for some suitable model parameters. Notice that a suppressed evolution with respect to SFH is commonly found for FRBs. In particular, we independently confirm that the FRB distribution model tracking SFH can be rejected at very high confidence. On the other hand, all the ``successful'' models effectively require a certain degree of ``delay'' with respect to SFH. These results might shed light on the origin of FRBs and FRB cosmology.

astro-ph.HE↗

arXiv2022

S2Looking: A Satellite Side-Looking Dataset for Building Change Detection

Building-change detection underpins many important applications, especially in the military and crisis-management domains. Recent methods used for change detection have shifted towards deep learning, which depends on the quality of its training data. The assembly of large-scale annotated satellite imagery datasets is therefore essential for global building-change surveillance. Existing datasets almost exclusively offer near-nadir viewing angles. This limits the range of changes that can be detected. By offering larger observation ranges, the scroll imaging mode of optical satellites presents an opportunity to overcome this restriction. This paper therefore introduces S2Looking, a building-change-detection dataset that contains large-scale side-looking satellite images captured at various off-nadir angles. The dataset consists of 5000 bitemporal image pairs of rural areas and more than 65,920 annotated instances of changes throughout the world. The dataset can be used to train deep-learning-based change-detection algorithms. It expands upon existing datasets by providing (1) larger viewing angles; (2) large illumination variances; and (3) the added complexity of rural images. To facilitate {the} use of the dataset, a benchmark task has been established, and preliminary tests suggest that deep-learning algorithms find the dataset significantly more challenging than the closest-competing near-nadir dataset, LEVIR-CD+. S2Looking may therefore promote important advances in existing building-change-detection algorithms. The dataset is available at https://github.com/S2Looking/.

cs.CV↗

arXiv2021

Deep Transfer Learning for Multi-source Entity Linkage via Domain Adaptation

Multi-source entity linkage focuses on integrating knowledge from multiple sources by linking the records that represent the same real world entity. This is critical in high-impact applications such as data cleaning and user stitching. The state-of-the-art entity linkage pipelines mainly depend on supervised learning that requires abundant amounts of training data. However, collecting well-labeled training data becomes expensive when the data from many sources arrives incrementally over time. Moreover, the trained models can easily overfit to specific data sources, and thus fail to generalize to new sources due to significant differences in data and label distributions. To address these challenges, we present AdaMEL, a deep transfer learning framework that learns generic high-level knowledge to perform multi-source entity linkage. AdaMEL models the attribute importance that is used to match entities through an attribute-level self-attention mechanism, and leverages the massive unlabeled data from new data sources through domain adaptation to make it generic and data-source agnostic. In addition, AdaMEL is capable of incorporating an additional set of labeled data to more accurately integrate data sources with different attribute importance. Extensive experiments show that our framework achieves state-of-the-art results with 8.21% improvement on average over methods based on supervised learning. Besides, it is more stable in handling different sets of data sources in less runtime.

cs.LG↗

arXiv2021

Inverse Chameleon Mechanism and Mass Limits for Compact Stars

As is well known, there are various mass limits for compact stars. For example, the maximum mass for non-rotating white dwarfs is given by the famous Chandrasekhar limit about $1.4 M_\odot$ (solar masses). Although the mass limit for neutron stars is not so clear to date, one of the widely accepted values is about $2.1 M_\odot\,$. Recently, challenges to these mass limits appeared. Motivated by the super-Chandrasekhar mass white dwarfs with masses up to $2.4 \sim 2.8 M_\odot\,$, and compact objects (probably neutron stars) in the mass gap (from $2.5 M_\odot$ or $3 M_\odot$ to $5 M_\odot$) inferred from gravitational waves detected by LIGO/Virgo in the third observing run (O3), we reconsider the mass limits for compact stars in the present work. Without invoking strong magnetic field and/or exotic equation of state (EOS), we try to increase the mass limits for compact stars in modified gravity theory. In this work, we propose an inverse chameleon mechanism, and show that the fifth-force mediated by the scalar field can evade the severe tests on earth, in solar system and universe, but manifest itself in compact stars such as white dwarfs and neutron stars. The mass limits for compact stars in the inverse chameleon mechanism can be easily increased to $3 M_\odot\,$, $5 M_\odot$ or even larger. We argue that the inverse chameleon mechanism might be constrained by the observations of exoplanets orbiting compact stars (such as white dwarfs and neutron stars), and gravitational waves from the last stage of binary compact star coalescence.

gr-qc↗