检索结果-内蒙古大学图书馆

Segment Together: A Versatile Paradigm for Semi-Supervised Medical Image Segmentation

学校读者我要写书评

暂无评论

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Zeng, Qingjie Xie, Yutong Lu, Zilin Lu, Mengkang Wu, Yicheng Xia, Yong Northwestern Polytechnical University National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Xi’an710072 China The University of Adelaide Australian Institute for Machine Learning AdelaideSA5000 Australia Monash University Faculty of Information Technology Department of Data Science and AI Australia

The scarcity of annotations has become a significant obstacle in training powerful deep-learning models for medical image segmentation, limiting their clinical application. To overcome this, semi-supervised learning that leverages abundant unlabeled data is highly desirable to enhance model training. However, most existing works still focus on specific medical tasks and underestimate the potential of learning across diverse tasks and datasets. In this paper, we propose a Versatile Semi-supervised framework (VerSemi) to present a new perspective that integrates various SSL tasks into a unified model with an extensive label space, exploiting more unlabeled data for semi-supervised medical image segmentation. Specifically, we introduce a dynamic task-prompted design to segment various targets from different datasets. Next, this unified model is used to identify the foreground regions from all labeled data, capturing cross-dataset semantics. Particularly, we create a synthetic task with a CutMix strategy to augment foreground targets within the expanded label space. To effectively utilize unlabeled data, we introduce a consistency constraint that aligns aggregated predictions from various tasks with those from the synthetic task, further guiding the model to accurately segment foreground regions during training. We evaluated our VerSemi framework against seven established SSL methods on four public benchmarking datasets. Our results suggest that VerSemi consistently outperforms all competing methods, beating the second-best method with a 2.69% average Dice gain on four datasets and setting a new state of the art for semi-supervised medical image segmentation. Code is available at https://***/maxwell0027/VerSemi. © 1982-2012 IEEE.

关键词： Self-supervised learning

Minimax rates for heterogeneous causal effect estimation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kennedy, Edward H. Balakrishnan, Sivaraman Robins, James M. Wasserman, Larry Department of Statistics & Data Science Carnegie Mellon University United States Machine Learning Department Carnegie Mellon University United States Departments of Biostatistics and Epidemiology Harvard University United States

Estimation of heterogeneous causal effects – i.e., how effects of policies and treatments vary across subjects – is a fundamental task in causal inference. Many methods for estimating conditional average treatment effects (CATEs) have been proposed in recent years, but questions surrounding optimality have remained largely unanswered. In particular, a minimax theory of optimality has yet to be developed, with the minimax rate of convergence and construction of rate-optimal estimators remaining open problems. In this paper we derive the minimax rate for CATE estimation, in a Hölder-smooth nonparametric model, and present a new local polynomial estimator, giving high-level conditions under which it is minimax optimal. Our minimax lower bound is derived via a localized version of the method of fuzzy hypotheses, combining lower bound constructions for nonparametric regression and functional estimation. Our proposed estimator can be viewed as a local polynomial R-Learner, based on a localized modification of higher-order influence function methods. The minimax rate we find exhibits several interesting features, including a non-standard elbow phenomenon and an unusual interpolation between nonparametric regression and functional estimation rates. The latter quantifies how the CATE, as an estimand, can be viewed as a regression/functional hybrid. © 2022, CC BY.

关键词： Optimization

Automating the selection of proxy variables of unmeasured confounders 24

学校读者我要写书评

暂无评论

Automating the selection of proxy variables of unmeasured co...

Proceedings of the 41st International Conference on machine learning

作者： Feng Xie Zhengming Chen Shanshan Luo Wang Miao Ruichu Cai Zhi Geng Department of Applied Statistics Beijing Technology and Business University Beijing China School of Computer Science Guangdong University of Technology Guangzhou China and Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi UAE Department of Probability and Statistics Peking University Beijing China School of Computer Science Guangdong University of Technology Guangzhou China

Recently, interest has grown in the use of proxy variables of unobserved confounding for inferring the causal effect in the presence of unmeasured confounders from observational data. One difficulty inhibiting the practical use is finding valid proxy variables of unobserved confounding to a target causal effect of interest. These proxy variables are typically justified by background knowledge. In this paper, we investigate the estimation of causal effects among multiple treatments and a single outcome, all of which are affected by unmeasured confounders, within a linear causal model, without prior knowledge of the validity of proxy variables. To be more specific, we first extend the existing proxy variable estimator, originally addressing a single unmeasured confounder, to accommodate scenarios where multiple unmeasured confounders exist between the treatments and the outcome. Subsequently, we present two different sets of precise identifiability conditions for selecting valid proxy variables of unmeasured confounders, based on the second-order statistics and higher-order statistics of the data, respectively. Moreover, we propose two data-driven methods for the selection of proxy variables and for the unbiased estimation of causal effects. Theoretical analysis demonstrates the correctness of our proposed algorithms. Experimental results on both synthetic and real-world data show the effectiveness of the proposed approach.

关键词：

Global High Categorical Resolution Land Cover Mapping via Weak Supervision

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tong, Xin-Yi Dong, Runmin Zhu, Xiao Xiang Chair of Data Science in Earth Observation Technical University of Munich Germany Ministry of Education Key Laboratory for Earth System Modeling Department of Earth System Science Tsinghua University China Munich Center for Machine Learning Germany

Land cover information is indispensable for advancing the United Nations’ sustainable development goals, and land cover mapping under a more detailed category system would significantly contribute to economic livelihood tracking and environmental degradation measurement. However, the substantial difficulty in acquiring fine-grained training data makes the implementation of this task particularly challenging. Here, we propose to combine fully labeled source domain and weakly labeled target domain for weakly supervised domain adaptation (WSDA). This is beneficial as the utilization of sparse and coarse weak labels can considerably alleviate the labor required for precise and detailed land cover annotation. Specifically, we introduce the Prototype-based pseudo-label Rectification and Expansion (PRE) approach, which leverages the prototypes (i.e., the class-wise feature centroids) as the bridge to connect sparse labels and global feature distributions. According to the feature distances to the prototypes, the confidence of pseudo-labels predicted in the unlabeled regions of the target domain is assessed. This confidence is then utilized to guide the dynamic expansion and rectification of pseudo-labels. Based on PRE, we carry out high categorical resolution land cover mapping for 10 cities in different regions around the world, severally using PlanetScope, Gaofen-1, and Sentinel-2 satellite images. In the study areas, we achieve cross-sensor, cross-category, and cross-continent WSDA, with the overall accuracy exceeding 80%. The promising results indicate that PRE is capable of reducing the dependency of land cover classification on high-quality annotations, thereby improving label efficiency. We expect our work to enable global fine-grained land cover mapping, which in turn promote Earth observation to provide more precise and thorough information for environmental monitoring. Copyright © 2024, The Authors. All rights reserved.

关键词： Expansion

An Optimized Hybrid Deep learning and IoT-Enabled Health System in Retina Image Analysis for Blindness Detection

学校读者我要写书评

暂无评论

An Optimized Hybrid Deep Learning and IoT-Enabled Health Sys...

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： J Yamini T Kanimozhi A Jenefa K Bagyalakshmi K Aarthi P Dhivya Department of Artificial Intelligence and Machine learning Kalaignar Karunanidhi Institute of Technology Coimbatore India Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore India Department of Computer Science and Engineering PPG Institute of Technology Coimbatore India Department of Mathematics SNS College of Technology Coimbatore India Department of Artificial Intelligence and Data Science Kalaignar Karunanidhi Institute of Technology Coimbatore India Department of Computer Science and Engineering Bannari Amman Institute of Technology Erode India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

Early signs of blind identification and retina disorder in retina image has become prominent. Deep learning techniques are used to improve the accuracy in detecting pathological conditions from the retina images. However, the models have some challenges such as suboptimal feature extraction and inefficient filtering methods. Most of the traditional methods often result in overfitting and under fitting, thus decreasing the generalizability and robustness of the model. The proposed hybrid approach combines bilateral filtering with Convolutional Neural Networks (CNN). In this approach, bilateral filtering acts as a pre-processing technique to enhance image quality by reducing noise and preserving edges for the correct extraction of features. The CNN is applied for feature extraction and it is used to self-learn complex patterns from filtered images. The proposed approach gives an accuracy of $95.65 \%$ with a loss of 0.18 without overfitting and underfitting.

关键词： Optical filters Accuracy Filtering Noise Predictive models Retina Feature extraction Convolutional neural networks Diseases Overfitting

Model and feature diversity for bayesian neural networks in mutual learning 23

学校读者我要写书评

暂无评论

Model and feature diversity for bayesian neural networks in ...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Cuong Pham Cuong C. Nguyen Trung Le Dinh Phung Gustavo Carneiro Thanh-Toan Do Department of Data Science and AI Monash University Australia Australian Institute for Machine Learning University of Adelaide Australia Department of Data Science and AI Monash University Australia and VinAI Vietnam Centre for Vision Speech and Signal Processing University of Surrey United Kingdom

Bayesian Neural Networks (BNNs) offer probability distributions for model parameters, enabling uncertainty quantification in predictions. However, they often underperform compared to deterministic neural networks. Utilizing mutual learning can effectively enhance the performance of peer BNNs. In this paper, we propose a novel approach to improve BNNs performance through deep mutual learning. The proposed approaches aim to increase diversity in both network parameter distributions and feature distributions, promoting peer networks to acquire distinct features that capture different characteristics of the input, which enhances the effectiveness of mutual learning. Experimental results demonstrate significant improvements in the classification accuracy, negative log-likelihood, and expected calibration error when compared to traditional mutual learning for BNNs.

关键词：

FTBC: Forward Temporal Bias Correction for Optimizing ANN-SNN Conversion

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Xiaofeng Bojkovic, Velibor Gu, Bin Suo, Kun Zou, Kai Faculty of Data Science City University of Macau China Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates Department of Computer Science Kennesaw State University GA United States ProtagoLabs Inc.

Spiking Neural Networks (SNNs) offer a promising avenue for energy-efficient computing compared with Artificial Neural Networks (ANNs), closely mirroring biological neural processes. However, this potential comes with inherent challenges in directly training SNNs through spatio-temporal backpropagation - stemming from the temporal dynamics of spiking neurons and their discrete signal processing - which necessitates alternative ways of training, most notably through ANN-SNN conversion. In this work, we introduce a lightweight Forward Temporal Bias Correction (FTBC) technique, aimed at enhancing conversion accuracy without the computational overhead. We ground our method on provided theoretical findings that through proper temporal bias calibration the expected error of ANN-SNN conversion can be reduced to be zero after each time step. We further propose a heuristic algorithm for finding the temporal bias only in the forward pass, thus eliminating the computational burden of backpropagation and we evaluate our method on CIFAR-10/100 and ImageNet datasets, achieving a notable increase in accuracy on all datasets. Codes are released at a GitHub repository. Copyright © 2024, The Authors. All rights reserved.

关键词： Heuristic algorithms

Real-Time Estimation of COVID-19 Infections: Deconvolution and Sensor Fusion

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Jahja, Maria Chin, Andrew Tibshirani, Ryan J. Department of Statistics & Data Science Machine Learning Department Carnegie Mellon University PittsburghPA United States

We propose, implement, and evaluate a method to estimate the daily number of new symptomatic COVID-19 infections, at the level of individual U.S. counties, by deconvolving daily reported COVID-19 case counts using an estimated symptom-onset-to-case-report delay distribution. Importantly, we focus on estimating infections in real-time (rather than retrospectively), which poses numerous challenges. To address these, we develop new methodology for both the distribution estimation and deconvolution steps, and we employ a sensor fusion layer (which fuses together predictions from models that are trained to track infections based on auxiliary surveillance streams) in order to improve accuracy and stability. Copyright © 2021, The Authors. All rights reserved.

关键词： machine learning

Disease and Medications Text Visualization Using Scattertext

学校读者我要写书评

暂无评论

Disease and Medications Text Visualization Using Scattertext

2025 International Conference on Intelligent Control, Computing and Communications, IC3 2025

作者： Rama Krishna, K. Sandhya, Kaipa Praveen Gujjar, J. Devadas, Raghavendra M. Hiremani, Vani Sapna, R. Impact college of Engineering and Applied Sciences Department of Artificial Intelligence and Machine Learning Bengaluru India Impact college of Engineering and applied sciences Department of Data Science Bengaluru India Faculty of Management Studies Bengaluru India Department of Information Technology Manipal India University Pune India

ISBN: (纸本)9798331527495

Before text data can be analysed and visualised, it must be thoroughly cleaned due to its messy nature. data visualizations use the data to tell an engaging and simple-to-read story. That is what the Scattertext tool does. Scatter text allows which terms stand out in your corpora and how their frequency varies across categories. The dataset used in this paper includes reviews of drugs. This dataset offers a useful window into how people discuss their thoughts and experiences using various drugs. The drug names, user ratings, and the actual written reviews are among the details included in the dataset. This dataset consists of drug reviews collected from various sources, hence expressing a wide range of opinions and feelings. Each row in this dataset represents the experience a user had with a given medication and hence allows us to explore those emotions that are associated with any particular set of drugs. Understanding opinion expressed in the review about drugs might go a long way in helping decision-making processes in both healthcare and pharmaceuticals. The scatter plot distinguishes between labelled points and unlabelled ones by using a custom algorithm for Scattertext. By hovering their cursor over the labelled areas done client-side, users can interactively see which terms correspond to which points. © 2025 IEEE.

关键词： data visualization