arXiv subjects

Heng Li

Publications and source records attributed to Heng Li.

At least 145 records · Page 8Linked to original sources

arXiv2024

Localizing axial dense emitters based on single-helix point spread function and deep learning

Stimulated Emission Depletion Microscopy (STED) can achieve a spatial resolution as high as several nanometers. As a point scanning imaging method, it requires 3D scanning to complete the imaging of 3D samples. The time-consuming 3D scanning can be compressed into a 2D one in the non-diffracting Bessel-Bessel STED (BB-STED) where samples are effectively excited by an optical needle. However, the image is just the 2D projection, i.e., there is no real axial resolution. Therefore, we propose a method to encode axial information to axially dense emitters by using a detection optical path with single-helix point spread function (SH-PSF), and then predicted the depths of the emitters by means of deep learning. Simulation demonstrated that, for a density 1~ 20 emitters in a depth range of 4 nm, an axial precision of ~35 nm can be achieved. Our method also works for experimental data, and an axial precision of ~63 nm can be achieved.

physics.optics↗

arXiv2024

Refining GPT-3 Embeddings with a Siamese Structure for Technical Post Duplicate Detection

One goal of technical online communities is to help developers find the right answer in one place. A single question can be asked in different ways with different wordings, leading to the existence of duplicate posts on technical forums. The question of how to discover and link duplicate posts has garnered the attention of both developer communities and researchers. For example, Stack Overflow adopts a voting-based mechanism to mark and close duplicate posts. However, addressing these constantly emerging duplicate posts in a timely manner continues to pose challenges. Therefore, various approaches have been proposed to detect duplicate posts on technical forum posts automatically. The existing methods suffer from limitations either due to their reliance on handcrafted similarity metrics which can not sufficiently capture the semantics of posts, or their lack of supervision to improve the performance. Additionally, the efficiency of these methods is hindered by their dependence on pair-wise feature generation, which can be impractical for large amount of data. In this work, we attempt to employ and refine the GPT-3 embeddings for the duplicate detection task. We assume that the GPT-3 embeddings can accurately represent the semantics of the posts. In addition, by training a Siamese-based network based on the GPT-3 embeddings, we obtain a latent embedding that accurately captures the duplicate relation in technical forum posts. Our experiment on a benchmark dataset confirms the effectiveness of our approach and demonstrates superior performance compared to baseline methods. When applied to the dataset we constructed with a recent Stack Overflow dump, our approach attains a Top-1, Top-5, and Top-30 accuracy of 23.1%, 43.9%, and 68.9%, respectively. With a manual study, we confirm our approach's potential of finding unlabelled duplicates on technical forums.

cs.SE↗

arXiv2023

TDeLTA: A Light-weight and Robust Table Detection Method based on Learning Text Arrangement

The diversity of tables makes table detection a great challenge, leading to existing models becoming more tedious and complex. Despite achieving high performance, they often overfit to the table style in training set, and suffer from significant performance degradation when encountering out-of-distribution tables in other domains. To tackle this problem, we start from the essence of the table, which is a set of text arranged in rows and columns. Based on this, we propose a novel, light-weighted and robust Table Detection method based on Learning Text Arrangement, namely TDeLTA. TDeLTA takes the text blocks as input, and then models the arrangement of them with a sequential encoder and an attention module. To locate the tables precisely, we design a text-classification task, classifying the text blocks into 4 categories according to their semantic roles in the tables. Experiments are conducted on both the text blocks parsed from PDF and extracted by open-source OCR tools, respectively. Compared to several state-of-the-art methods, TDeLTA achieves competitive results with only 3.1M model parameters on the large-scale public datasets. Moreover, when faced with the cross-domain data under the 0-shot setting, TDeLTA outperforms baselines by a large margin of nearly 7%, which shows the strong robustness and transferability of the proposed model.

cs.CL↗

arXiv2023

AutoRepo: A general framework for multi-modal LLM-based automated construction reporting

Ensuring the safety, quality, and timely completion of construction projects is paramount, with construction inspections serving as a vital instrument towards these goals. Nevertheless, the predominantly manual approach of present-day inspections frequently results in inefficiencies and inadequate information management. Such methods often fall short of providing holistic, exhaustive assessments, consequently engendering regulatory oversights and potential safety hazards. To address this issue, this paper presents a novel framework named AutoRepo for automated generation of construction inspection reports. The unmanned vehicles efficiently perform construction inspections and collect scene information, while the multimodal large language models (LLMs) are leveraged to automatically generate the inspection reports. The framework was applied and tested on a real-world construction site, demonstrating its potential to expedite the inspection process, significantly reduce resource allocation, and produce high-quality, regulatory standard-compliant inspection reports. This research thus underscores the immense potential of multimodal large language models in revolutionizing construction inspection practices, signaling a significant leap forward towards a more efficient and safer construction management paradigm.

cs.AI↗

arXiv2023

Enhancing and Adapting in the Clinic: Source-free Unsupervised Domain Adaptation for Medical Image Enhancement

Medical imaging provides many valuable clues involving anatomical structure and pathological characteristics. However, image degradation is a common issue in clinical practice, which can adversely impact the observation and diagnosis by physicians and algorithms. Although extensive enhancement models have been developed, these models require a well pre-training before deployment, while failing to take advantage of the potential value of inference data after deployment. In this paper, we raise an algorithm for source-free unsupervised domain adaptive medical image enhancement (SAME), which adapts and optimizes enhancement models using test data in the inference phase. A structure-preserving enhancement network is first constructed to learn a robust source model from synthesized training data. Then a teacher-student model is initialized with the source model and conducts source-free unsupervised domain adaptation (SFUDA) by knowledge distillation with the test data. Additionally, a pseudo-label picker is developed to boost the knowledge distillation of enhancement tasks. Experiments were implemented on ten datasets from three medical image modalities to validate the advantage of the proposed algorithm, and setting analysis and ablation studies were also carried out to interpret the effectiveness of SAME. The remarkable enhancement performance and benefits for downstream tasks demonstrate the potential and generalizability of SAME. The code is available at https://github.com/liamheng/Annotation-free-Medical-Image-Enhancement.

eess.IV↗

arXiv2023

Hypergraphs with infinitely many extremal constructions

We give the first exact and stability results for a hypergraph Turán problem with infinitely many extremal constructions that are far from each other in edit-distance. This includes an example of triple systems with Turán density $2/9$, thus answering some questions posed by the third and fourth authors and Reiher about the feasible region of hypergraphs. Our results also provide extremal constructions whose shadow density is a transcendental number. Our novel approach is to construct certain multilinear polynomials that attain their maximum (in the standard simplex) on a line segment and then to use these polynomials to define an operation on hypergraphs that gives extremal constructions.

math.CO↗

arXiv2023

Many vertex-disjoint even cycles of fixed length in a graph

For every integer $k \ge 3$, we determine the extremal structure of an $n$-vertex graph with at most $t$ vertex-disjoint copies of $C_{2k}$ when $n$ is sufficiently large and $t$ lies in the interval $\left[\frac{\mathrm{ex}(n,C_{2k})}{\varepsilon n}, \varepsilon n\right]$, where $\varepsilon>0$ is a constant depending only on $k$. The question for $k = 2$ and $t = o\left(\frac{\mathrm{ex}(n,C_{2k})}{n}\right)$ was explored in prior work~\cite{HHLLYZ23a}, revealing different extremal structures in these cases. Our result can be viewed as an extension of the theorems by Egawa~\cite{Ega96} and Verstraëte~\cite{Ver03}, where the focus was on the existence of many vertex-disjoint cycles of the same length without any length constraints.

math.CO↗

arXiv2023

A Large-Scale Exploratory Study of Android Sports Apps in the Google Play Store

Prior studies on mobile app analysis often analyze apps across different categories or focus on a small set of apps within a category. These studies either provide general insights for an entire app store which consists of millions of apps, or provide specific insights for a small set of apps. However, a single app category can often contain tens of thousands to hundreds of thousands of apps. For example, according to AppBrain, there are 46,625 apps in the "Sports" category of Google Play apps. Analyzing such a targeted category of apps can provide more specific insights than analyzing apps across categories while still benefiting many app developers interested in the category. This work aims to study a large number of apps from a single category (i.e., the sports category). We performed an empirical study on over two thousand sports apps in the Google Play Store. We study the characteristics of these apps (e.g., their targeted sports types and main functionalities) through manual analysis, the topics in the user review through topic modeling, as well as the aspects that contribute to the negative opinions of users through analysis of user ratings and sentiment. It is concluded that analyzing a targeted category of apps (e.g., sports apps) can provide more specific insights than analyzing apps across different categories while still being relevant for a large number (e.g., tens of thousands) of apps. Besides, as a rapid-growing and competitive market, sports apps provide rich opportunities for future research, for example, to study the integration of data science or machine learning techniques in software applications or to study the factors that influence the competitiveness of the apps.

cs.SE↗

arXiv2023

ACT-Net: Anchor-context Action Detection in Surgery Videos

Recognition and localization of surgical detailed actions is an essential component of developing a context-aware decision support system. However, most existing detection algorithms fail to provide high-accuracy action classes even having their locations, as they do not consider the surgery procedure's regularity in the whole video. This limitation hinders their application. Moreover, implementing the predictions in clinical applications seriously needs to convey model confidence to earn entrustment, which is unexplored in surgical action prediction. In this paper, to accurately detect fine-grained actions that happen at every moment, we propose an anchor-context action detection network (ACTNet), including an anchor-context detection (ACD) module and a class conditional diffusion (CCD) module, to answer the following questions: 1) where the actions happen; 2) what actions are; 3) how confidence predictions are. Specifically, the proposed ACD module spatially and temporally highlights the regions interacting with the extracted anchor in surgery video, which outputs action location and its class distribution based on anchor-context interactions. Considering the full distribution of action classes in videos, the CCD module adopts a denoising diffusion-based generative model conditioned on our ACD estimator to further reconstruct accurately the action predictions. Moreover, we utilize the stochastic nature of the diffusion model outputs to access model confidence for each prediction. Our method reports the state-of-the-art performance, with improvements of 4.0% mAP against baseline on the surgical video dataset.

cs.CV↗

arXiv2023

Studying the Characteristics of AIOps Projects on GitHub

Artificial Intelligence for IT Operations (AIOps) leverages AI approaches to handle the massive amount of data generated during the operations of software systems. Prior works have proposed various AIOps solutions to support different tasks in system operations and maintenance, such as anomaly detection. In this study, we conduct an in-depth analysis of open-source AIOps projects to understand the characteristics of AIOps in practice. We first carefully identify a set of AIOps projects from GitHub and analyze their repository metrics (e.g., the used programming languages). Then, we qualitatively examine the projects to understand their input data, analysis techniques, and goals. Finally, we assess the quality of these projects using different quality metrics, such as the number of bugs. To provide context, we also sample two sets of baseline projects from GitHub: a random sample of machine learning projects and a random sample of general-purposed projects. By comparing different metrics between our identified AIOps projects and these baselines, we derive meaningful insights. Our results reveal a recent and growing interest in AIOps solutions. However, the quality metrics indicate that AIOps projects suffer from more issues than our baseline projects. We also pinpoint the most common issues in AIOps approaches and discuss potential solutions to address these challenges. Our findings offer valuable guidance to researchers and practitioners, enabling them to comprehend the current state of AIOps practices and shed light on different ways of improving AIOps' weaker aspects. To the best of our knowledge, this work marks the first attempt to characterize open-source AIOps projects.

cs.SE↗

arXiv2023

A Generic Fundus Image Enhancement Network Boosted by Frequency Self-supervised Representation Learning

Fundus photography is prone to suffer from image quality degradation that impacts clinical examination performed by ophthalmologists or intelligent systems. Though enhancement algorithms have been developed to promote fundus observation on degraded images, high data demands and limited applicability hinder their clinical deployment. To circumvent this bottleneck, a generic fundus image enhancement network (GFE-Net) is developed in this study to robustly correct unknown fundus images without supervised or extra data. Levering image frequency information, self-supervised representation learning is conducted to learn robust structure-aware representations from degraded images. Then with a seamless architecture that couples representation learning and image enhancement, GFE-Net can accurately correct fundus images and meanwhile preserve retinal structures. Comprehensive experiments are implemented to demonstrate the effectiveness and advantages of GFE-Net. Compared with state-of-the-art algorithms, GFE-Net achieves superior performance in data dependency, enhancement performance, deployment efficiency, and scale generalizability. Follow-up fundus image analysis is also facilitated by GFE-Net, whose modules are respectively verified to be effective for image enhancement.

eess.IV↗

arXiv2023

Deploying Deep Reinforcement Learning Systems: A Taxonomy of Challenges

Deep reinforcement learning (DRL), leveraging Deep Learning (DL) in reinforcement learning, has shown significant potential in achieving human-level autonomy in a wide range of domains, including robotics, computer vision, and computer games. This potential justifies the enthusiasm and growing interest in DRL in both academia and industry. However, the community currently focuses mostly on the development phase of DRL systems, with little attention devoted to DRL deployment. In this paper, we propose an empirical study on Stack Overflow (SO), the most popular Q&A forum for developers, to uncover and understand the challenges practitioners faced when deploying DRL systems. Specifically, we categorized relevant SO posts by deployment platforms: server/cloud, mobile/embedded system, browser, and game engine. After filtering and manual analysis, we examined 357 SO posts about DRL deployment, investigated the current state, and identified the challenges related to deploying DRL systems. Then, we investigate the prevalence and difficulty of these challenges. Results show that the general interest in DRL deployment is growing, confirming the study's relevance and importance. Results also show that DRL deployment is more difficult than other DRL issues. Additionally, we built a taxonomy of 31 unique challenges in deploying DRL to different platforms. On all platforms, RL environment-related challenges are the most popular, and communication-related challenges are the most difficult among practitioners. We hope our study inspires future research and helps the community overcome the most common and difficult challenges practitioners face when deploying DRL systems.

cs.LG↗

arXiv2023

Hypergraphs with irrational Turán density and many extremal configurations

Unlike graphs, determining Turán densities of hypergraphs is known to be notoriously hard in general. The essential reason is that for many classical families of $r$-uniform hypergraphs $\mathcal{F}$, there are perhaps many near-extremal $\mathcal{M}_t$-free configurations with very different structure. Such a phenomenon is called not stable, and Liu and Mubayi gave a first not stable example. Another perhaps reason is that little is known about the set consisting of all possible Turán densities which has cardinality of the continuum. Let $t\ge 2$ be an integer. In this paper, we construct a finite family $\mathcal{M}_t$ of 3-uniform hypergraphs such that the Turán density of $\mathcal{M}_t$ is irrational, and there are $t$ near-extremal $\mathcal{M}_t$-free configurations that are far from each other in edit-distance. This is the first not stable example that has an irrational Turán density. It also provides a new phenomenon about feasible region functions.

math.CO↗

arXiv2023

Genome assembly in the telomere-to-telomere era

De novo assembly is the process of reconstructing the genome sequence of an organism from sequencing reads. Genome sequences are essential to biology, and assembly has been a central problem in bioinformatics for four decades. Until recently, genomes were typically assembled into fragments of a few megabases at best but technological advances in long-read sequencing now enable near complete chromosome-level assembly, also known as telomere-to-telomere assembly, for many organisms. Here we review recent progress on assembly algorithms and protocols. We focus on how to derive near telomere-to-telomere assemblies and discuss potential future developments.

q-bio.GN↗

arXiv2023

Optimal battery thermal management for electric vehicles with battery degradation minimization

The control of a battery thermal management system (BTMS) is essential for the thermal safety, energy efficiency, and durability of electric vehicles (EVs) in hot weather. To address the battery cooling optimization problem, this paper utilizes dynamic programming (DP) to develop an online rule-based control strategy. Firstly, an electrical-thermal-aging model of the $\rm LiFePO_4$ battery pack is established. A control-oriented onboard BTMS model is proposed and verified under different speed profiles and temperatures. Then in the DP framework, a cost function consisting of battery aging cost and cooling-induced electricity cost is minimized to obtain the optimal compressor power. By exacting three rules "fast cooling, slow cooling, and temperature-maintaining" from the DP result, a near-optimal rule-based cooling strategy, which uses as much regenerative energy as possible to cool the battery pack, is proposed for online execution. Simulation results show that the proposed online strategy can dramatically improve the driving economy and reduce battery degradation under diverse operation conditions, achieving less than a 3% difference in battery loss compared to the offline DP. Recommendations regarding battery cooling under different real-world cases are finally provided.

eess.SY↗

arXiv2023

Frequency-mixed Single-source Domain Generalization for Medical Image Segmentation

The annotation scarcity of medical image segmentation poses challenges in collecting sufficient training data for deep learning models. Specifically, models trained on limited data may not generalize well to other unseen data domains, resulting in a domain shift issue. Consequently, domain generalization (DG) is developed to boost the performance of segmentation models on unseen domains. However, the DG setup requires multiple source domains, which impedes the efficient deployment of segmentation algorithms in clinical scenarios. To address this challenge and improve the segmentation model's generalizability, we propose a novel approach called the Frequency-mixed Single-source Domain Generalization method (FreeSDG). By analyzing the frequency's effect on domain discrepancy, FreeSDG leverages a mixed frequency spectrum to augment the single-source domain. Additionally, self-supervision is constructed in the domain augmentation to learn robust context-aware representations for the segmentation task. Experimental results on five datasets of three modalities demonstrate the effectiveness of the proposed algorithm. FreeSDG outperforms state-of-the-art methods and significantly improves the segmentation model's generalizability. Therefore, FreeSDG provides a promising solution for enhancing the generalization of medical image segmentation models, especially when annotated data is scarce. The code is available at https://github.com/liamheng/Non-IID_Medical_Image_Segmentation.

eess.IV↗

arXiv2023

Scalable telomere-to-telomere assembly for diploid and polyploid genomes with double graph

Despite recent advances in the length and the accuracy of long-read data, building haplotype-resolved genome assemblies from telomere to telomere still requires considerable computational resources. In this study, we present an efficient de novo assembly algorithm that combines multiple sequencing technologies to scale up population-wide telomere-to-telomere assemblies. By utilizing twenty-two human and two plant genomes, we demonstrate that our algorithm is around an order of magnitude cheaper than existing methods, while producing better diploid and haploid assemblies. Notably, our algorithm is the only feasible solution to the haplotype-resolved assembly of polyploid genomes.

q-bio.GN↗

arXiv2023

Learnable Ophthalmology SAM

Segmentation is vital for ophthalmology image analysis. But its various modal images hinder most of the existing segmentation algorithms applications, as they rely on training based on a large number of labels or hold weak generalization ability. Based on Segment Anything (SAM), we propose a simple but effective learnable prompt layer suitable for multiple target segmentation in ophthalmology multi-modal images, named Learnable Ophthalmology Segment Anything (SAM). The learnable prompt layer learns medical prior knowledge from each transformer layer. During training, we only train the prompt layer and task head based on a one-shot mechanism. We demonstrate the effectiveness of our thought based on four medical segmentation tasks based on nine publicly available datasets. Moreover, we only provide a new improvement thought for applying the existing fundamental CV models in the medical field. Our codes are available at \href{https://github.com/Qsingle/LearnablePromptSAM}{website}.

cs.CV↗