arXiv subjects

Yuxin Li

Publications and source records attributed to Yuxin Li.

68 records · Page 4Linked to original sources

arXiv2023

IQAGPT: Image Quality Assessment with Vision-language and ChatGPT Models

Large language models (LLMs), such as ChatGPT, have demonstrated impressive capabilities in various tasks and attracted an increasing interest as a natural language interface across many domains. Recently, large vision-language models (VLMs) like BLIP-2 and GPT-4 have been intensively investigated, which learn rich vision-language correlation from image-text pairs. However, despite these developments, the application of LLMs and VLMs in image quality assessment (IQA), particularly in medical imaging, remains to be explored, which is valuable for objective performance evaluation and potential supplement or even replacement of radiologists' opinions. To this end, this paper introduces IQAGPT, an innovative image quality assessment system integrating an image quality captioning VLM with ChatGPT for generating quality scores and textual reports. First, we build a CT-IQA dataset for training and evaluation, comprising 1,000 CT slices with diverse quality levels professionally annotated. To better leverage the capabilities of LLMs, we convert annotated quality scores into semantically rich text descriptions using a prompt template. Second, we fine-tune the image quality captioning VLM on the CT-IQA dataset to generate quality descriptions. The captioning model fuses the image and text features through cross-modal attention. Third, based on the quality descriptions, users can talk with ChatGPT to rate image quality scores or produce a radiological quality report. Our preliminary results demonstrate the feasibility of assessing image quality with large models. Remarkably, our IQAGPT outperforms GPT-4 and CLIP-IQA, as well as the multi-task classification and regression models that solely rely on images.

cs.CV↗

arXiv2023

Local-Global History-aware Contrastive Learning for Temporal Knowledge Graph Reasoning

Temporal knowledge graphs (TKGs) have been identified as a promising approach to represent the dynamics of facts along the timeline. The extrapolation of TKG is to predict unknowable facts happening in the future, holding significant practical value across diverse fields. Most extrapolation studies in TKGs focus on modeling global historical fact repeating and cyclic patterns, as well as local historical adjacent fact evolution patterns, showing promising performance in predicting future unknown facts. Yet, existing methods still face two major challenges: (1) They usually neglect the importance of historical information in KG snapshots related to the queries when encoding the local and global historical information; (2) They exhibit weak anti-noise capabilities, which hinders their performance when the inputs are contaminated with noise.To this end, we propose a novel \blue{Lo}cal-\blue{g}lobal history-aware \blue{C}ontrastive \blue{L}earning model (\blue{LogCL}) for TKG reasoning, which adopts contrastive learning to better guide the fusion of local and global historical information and enhance the ability to resist interference. Specifically, for the first challenge, LogCL proposes an entity-aware attention mechanism applied to the local and global historical facts encoder, which captures the key historical information related to queries. For the latter issue, LogCL designs four historical query contrast patterns, effectively improving the robustness of the model. The experimental results on four benchmark datasets demonstrate that LogCL delivers better and more robust performance than the state-of-the-art baselines.

cs.AI↗

arXiv2023

Hansel: A Chinese Few-Shot and Zero-Shot Entity Linking Benchmark

Modern Entity Linking (EL) systems entrench a popularity bias, yet there is no dataset focusing on tail and emerging entities in languages other than English. We present Hansel, a new benchmark in Chinese that fills the vacancy of non-English few-shot and zero-shot EL challenges. The test set of Hansel is human annotated and reviewed, created with a novel method for collecting zero-shot EL datasets. It covers 10K diverse documents in news, social media posts and other web articles, with Wikidata as its target Knowledge Base. We demonstrate that the existing state-of-the-art EL system performs poorly on Hansel (R@1 of 36.6% on Few-Shot). We then establish a strong baseline that scores a R@1 of 46.2% on Few-Shot and 76.6% on Zero-Shot on our dataset. We also show that our baseline achieves competitive results on TAC-KBP2015 Chinese Entity Linking task.

cs.CL↗

arXiv2023

Normalized solutions for Sobolev critical Schrödinger-Bopp-Podolsky systems

We study the Sobolev critical Schrödinger-Bopp-Podolsky system \begin{gather*} -Δu+ϕu=λu+μ|u|^{p-2}u+|u|^4u\quad \text{in }\mathbb{R}^3, -Δϕ+Δ^2ϕ=4πu^2\quad \text{in } \mathbb{R}^3, \end{gather*} under the mass constraint \[ \int_{\mathbb{R}^3}u^2\,dx=c \] for some prescribed $c>0$, where $2 0$ is a parameter, and $λ\in\mathbb{R}$ is a Lagrange multiplier. By developing a constraint minimizing approach, we show that the above system admits a local minimizer. Furthermore, we establish the existence of normalized ground state solutions.

math.AP↗

arXiv2023

Where and How: Mitigating Confusion in Neural Radiance Fields from Sparse Inputs

Neural Radiance Fields from Sparse input} (NeRF-S) have shown great potential in synthesizing novel views with a limited number of observed viewpoints. However, due to the inherent limitations of sparse inputs and the gap between non-adjacent views, rendering results often suffer from over-fitting and foggy surfaces, a phenomenon we refer to as "CONFUSION" during volume rendering. In this paper, we analyze the root cause of this confusion and attribute it to two fundamental questions: "WHERE" and "HOW". To this end, we present a novel learning framework, WaH-NeRF, which effectively mitigates confusion by tackling the following challenges: (i)"WHERE" to Sample? in NeRF-S -- we introduce a Deformable Sampling strategy and a Weight-based Mutual Information Loss to address sample-position confusion arising from the limited number of viewpoints; and (ii) "HOW" to Predict? in NeRF-S -- we propose a Semi-Supervised NeRF learning Paradigm based on pose perturbation and a Pixel-Patch Correspondence Loss to alleviate prediction confusion caused by the disparity between training and testing viewpoints. By integrating our proposed modules and loss functions, WaH-NeRF outperforms previous methods under the NeRF-S setting. Code is available https://github.com/bbbbby-99/WaH-NeRF.

cs.CV↗

arXiv2023

Delving into Semantic Scale Imbalance

Model bias triggered by long-tailed data has been widely studied. However, measure based on the number of samples cannot explicate three phenomena simultaneously: (1) Given enough data, the classification performance gain is marginal with additional samples. (2) Classification performance decays precipitously as the number of training samples decreases when there is insufficient data. (3) Model trained on sample-balanced datasets still has different biases for different classes. In this work, we define and quantify the semantic scale of classes, which is used to measure the feature diversity of classes. It is exciting to find experimentally that there is a marginal effect of semantic scale, which perfectly describes the first two phenomena. Further, the quantitative measurement of semantic scale imbalance is proposed, which can accurately reflect model bias on multiple datasets, even on sample-balanced data, revealing a novel perspective for the study of class imbalance. Due to the prevalence of semantic scale imbalance, we propose semantic-scale-balanced learning, including a general loss improvement scheme and a dynamic re-weighting training framework that overcomes the challenge of calculating semantic scales in real-time during iterations. Comprehensive experiments show that dynamic semantic-scale-balanced learning consistently enables the model to perform superiorly on large-scale long-tailed and non-long-tailed natural and medical datasets, which is a good starting point for mitigating the prevalent but unnoticed model bias.

cs.CV↗

arXiv2021

Interactive Medical Image Segmentation with Self-Adaptive Confidence Calibration

Medical image segmentation is one of the fundamental problems for artificial intelligence-based clinical decision systems. Current automatic medical image segmentation methods are often failed to meet clinical requirements. As such, a series of interactive segmentation algorithms are proposed to utilize expert correction information. However, existing methods suffer from some segmentation refining failure problems after long-term interactions and some cost problems from expert annotation, which hinder clinical applications. This paper proposes an interactive segmentation framework, called interactive MEdical segmentation with self-adaptive Confidence CAlibration (MECCA), by introducing the corrective action evaluation, which combines the action-based confidence learning and multi-agent reinforcement learning (MARL). The evaluation is established through a novel action-based confidence network, and the corrective actions are obtained from MARL. Based on the confidential information, a self-adaptive reward function is designed to provide more detailed feedback, and a simulated label generation mechanism is proposed on unsupervised data to reduce over-reliance on labeled data. Experimental results on various medical image datasets have shown the significant performance of the proposed algorithm.

cs.CV↗

arXiv2021

An Automatic Detection Method Of Cerebral Aneurysms In Time-Of-Flight Magnetic Resonance Angiography Images Based On Attention 3D U-Net

Background:Subarachnoid hemorrhage caused by ruptured cerebral aneurysm often leads to fatal consequences.However,if the aneurysm can be found and treated during asymptomatic periods,the probability of rupture can be greatly reduced.At present,time-of-flight magnetic resonance angiography is one of the most commonly used non-invasive screening techniques for cerebral aneurysm,and the application of deep learning technology in aneurysm detection can effectively improve the screening effect of aneurysm.Existing studies have found that three-dimensional features play an important role in aneurysm detection,but they require a large amount of training data and have problems such as a high false positive rate. Methods:This paper proposed a novel method for aneurysm detection.First,a fully automatic cerebral artery segmentation algorithm without training data was used to extract the volume of interest,and then the 3D U-Net was improved by the 3D SENet module to establish an aneurysm detection model.Eventually a set of fully automated,end-to-end aneurysm detection methods have been formed. Results:A total of 231 magnetic resonance angiography image data were used in this study,among which 132 were training sets,34 were internal test sets and 65 were external test sets.The presented method obtained 97.89% sensitivity in the five-fold cross-validation and obtained 91.0% sensitivity with 2.48 false positives/case in the detection of the external test sets. Conclusions:Compared with the results of our previous studies and other studies,the method in this paper achieves a very competitive sensitivity with less training data and maintains a low false positive rate.As the only method currently using 3D U-Net for aneurysm detection,it proves the feasibility and superior performance of this network in aneurysm detection,and also explores the potential of the channel attention mechanism in this task.

eess.IV↗

arXiv2021

Deep Learning-based Segmentation of Cerebral Aneurysms in 3D TOF-MRA using Coarse-to-Fine Framework

BACKGROUND AND PURPOSE: Cerebral aneurysm is one of the most common cerebrovascular diseases, and SAH caused by its rupture has a very high mortality and disability rate. Existing automatic segmentation methods based on DLMs with TOF-MRA modality could not segment edge voxels very well, so that our goal is to realize more accurate segmentation of cerebral aneurysms in 3D TOF-MRA with the help of DLMs. MATERIALS AND METHODS: In this research, we proposed an automatic segmentation framework of cerebral aneurysm in 3D TOF-MRA. The framework was composed of two segmentation networks ranging from coarse to fine. The coarse segmentation network, namely DeepMedic, completed the coarse segmentation of cerebral aneurysms, and the processed results were fed into the fine segmentation network, namely dual-channel SE_3D U-Net trained with weighted loss function, for fine segmentation. Images from ADAM2020 (n=113) were used for training and validation and images from another center (n=45) were used for testing. The segmentation metrics we used include DSC, HD, and VS. RESULTS: The trained cerebral aneurysm segmentation model achieved DSC of 0.75, HD of 1.52, and VS of 0.91 on validation cohort. On the totally independent test cohort, our method achieved the highest DSC of 0.12, the lowest HD of 11.61, and the highest VS of 0.16 in comparison with state-of-the-art segmentation networks. CONCLUSIONS: The coarse-to-fine framework, which composed of DeepMedic and dual-channel SE_3D U-Net can segment cerebral aneurysms in 3D TOF-MRA with a superior accuracy.

eess.IV↗

arXiv2021

Composition based crystal materials symmetry prediction using machine learning with enhanced descriptors

Geometric information such as the space groups and crystal systems plays an important role in the properties of crystal materials. Prediction of crystal system and space group thus has wide applications in crystal material property estimation and structure prediction. Previous works on experimental X-ray diffraction (XRD) and density functional theory (DFT) based structure determination methods achieved outstanding performance, but they are not applicable for large-scale screening of materials compositions. There are also machine learning models using Magpie descriptors for composition based material space group determination, but their prediction accuracy only ranges between 0.638 and 0.907 in different kinds of crystals. Herein, we report an improved machine learning model for predicting the crystal system and space group of materials using only the formula information. Benchmark study on a dataset downloaded from Materials Project Database shows that our random forest models based on our new descriptor set, achieve significant performance improvements compared with previous work with accuracy scores ranging between 0.712 and 0.961 in terms of space group classification. Our model also shows large performance improvement for crystal system prediction. Trained models and source code are freely available at \url{https://github.com/Yuxinya/SG_predict}

cond-mat.mtrl-sci↗

arXiv2021

Crystal structure prediction of materials with high symmetry using differential evolution

Crystal structure determines properties of materials. With the crystal structure of a chemical substance, many physical and chemical properties can be predicted by first-principles calculations or machine learning models. Since it is relatively easy to generate a hypothetical chemically valid formula, crystal structure prediction becomes an important method for discovering new materials. In our previous work, we proposed a contact map-based crystal structure prediction method, which uses global optimization algorithms such as genetic algorithms to maximize the match between the contact map of the predicted structure and the contact map of the real crystal structure to search for the coordinates at the Wyckoff Positions(WP). However, when predicting the crystal structure with high symmetry, we found that the global optimization algorithm has difficulty to find an effective combination of WPs that satisfies the chemical formula, which is mainly caused by the inconsistency between the dimensionality of the contact map of the predicted crystal structure and the dimensionality of the contact map of the target crystal structure. This makes it challenging to predict the crystal structures of high-symmetry crystals. In order to solve this problem, here we propose to use PyXtal to generate and filter random crystal structures with given symmetry constraints based on the information such as chemical formulas and space groups. With contact map as the optimization goal, we use differential evolution algorithms to search for non-special coordinates at the Wyckoff positions to realize the structure prediction of high-symmetry crystal materials. Our experimental results show that our proposed algorithm CMCrystalHS can effectively solve the problem of inconsistent contact map dimensions and predict the crystal structures with high symmetry.

cond-mat.mtrl-sci↗

arXiv2021

Maximal and Maximum Dissociation Sets in General and Triangle-Free Graphs

A subset of vertices $F$ in a graph $G$ is called a \emph{dissociation set} if the induced subgraph $G[F]$ of $G$ has maximum degree at most 1. A \emph{maximal dissociation set} of $G$ is a dissociation set which is not a proper subset of any other dissociation sets. A \emph{maximum dissociation set} is a dissociation set of maximum size. We show that every graph of order $n$ has at most $10^{\frac{n}{5}}$ maximal dissociation sets, and that every triangle-free graph of order $n$ has at most $6^{\frac{n}{4}}$ maximal dissociation sets. We also characterize the extremal graphs on which these upper bounds are attained. The tight upper bounds on the number of maximum dissociation sets in general and triangle-free graphs are also obtained.

math.CO↗

arXiv2021

Contact Map based Crystal Structure Prediction using Global Optimization

Crystal structure prediction is now playing an increasingly important role in discovery of new materials. Global optimization methods such as genetic algorithms (GA) and particle swarm optimization (PSO) have been combined with first principle free energy calculations to predict crystal structures given composition or only a chemical system. While these approaches can exploit certain crystal patterns such as symmetry and periodicity in their search process, they usually do not exploit the large amount of implicit rules and constraints of atom configurations embodied in the large number of known crystal structures. They currently can only handle crystal structure prediction of relatively small systems. Inspired by the knowledge-rich protein structure prediction approach, herein we explore whether known geometric constraints such as the atomic contact map of a target crystal material can help predict its structure given its space group information. We propose a global optimization based algorithm, CMCrystal, for crystal structure reconstruction based on atomic contact maps. Based on extensive experiments using six global optimization algorithms, we show that it is viable to reconstruct the crystal structure given the atomic contact map for some crystal materials but more constraints are needed for other target materials to achieve successful reconstruction. This implies that atomic interaction information learned from existing materials can be used to improve crystal structure prediction.

cond-mat.mtrl-sci↗

arXiv2020

MLatticeABC: Generic Lattice Constant Prediction of Crystal Materials using Machine Learning

Lattice constants such as unit cell edge lengths and plane angles are important parameters of the periodic structures of crystal materials. Predicting crystal lattice constants has wide applications in crystal structure prediction and materials property prediction. Previous work has used machine learning models such as neural networks and support vector machines combined with composition features for lattice constant prediction and has achieved a maximum performance for cubic structures with an average $R^2$ of 0.82. Other models tailored for special materials family of a fixed form such as ABX3 perovskites can achieve much higher performance due to the homogeneity of the structures. However, these models trained with small datasets are usually not applicable to generic lattice parameter prediction of materials with diverse compositions. Herein, we report MLatticeABC, a random forest machine learning model with a new descriptor set for lattice unit cell edge length ($a,b,c$) prediction which achieves an R2 score of 0.979 for lattice parameter $a$ of cubic crystals and significant performance improvement for other crystal systems as well. Source code and trained models can be freely accessed at https://github.com/usccolumbia/MLatticeABC

cond-mat.mtrl-sci↗