检索结果-内蒙古大学图书馆

MetAug: Contrastive Learning via Meta Feature Augmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Jiangmeng Qiang, Wenwen Zheng, Changwen Su, Bing Xiong, Hui Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Guangdong China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Guangzhou China Department of Computer Science Engineering The Hong Kong University of Science and Technology Hong Kong

What matters for contrastive learning? We argue that contrastive learning heavily relies on informative features, or "hard" (positive or negative) features. Early works include more informative features by applying complex data augmentations and large batch size or memory bank, and recent works design elaborate sampling approaches to explore informative features. The key challenge toward exploring such features is that the source multi-view data is generated by applying random data augmentations, making it infeasible to always add useful information in the augmented data. Consequently, the informativeness of features learned from such augmented data is limited. In response, we propose to directly augment the features in latent space, thereby learning discriminative representations without a large amount of input data. We perform a meta learning technique to build the augmentation generator that updates its network parameters by considering the performance of the encoder. However, insufficient input data may lead the encoder to learn collapsed features and therefore malfunction the augmentation generator. A new margin-injected regularization is further added in the objective function to avoid the encoder learning a degenerate mapping. To contrast all features in one gradient back-propagation step, we adopt the proposed optimization-driven unified contrastive loss instead of the conventional contrastive loss. Empirically, our method achieves state-of-the-art results on several benchmark datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Backpropagation

A Comprehensive Survey for Hyperspectral Image Classification: The Evolution from Conventional to Transformers and Mamba Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ahmad, Muhammad Distefano, Salvatore Khan, Adil Mehmood Mazzara, Manuel Li, Chenyu Li, Hao Aryal, Jagannath Ding, Yao Vivone, Gemine Hong, Danfeng Department of Computer Science National University of Computer and Emerging Sciences Islamabad Pakistan Dipartimento di Matematica e Informatica-MIFT University of Messina Messina98121 Italy School of Computer Science University of Hull HullHU6 7RX United Kingdom Institute of Software Development and Engineering Innopolis University Innopolis420500 Russia Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Big Geospatial Data Management Technical University of Munich Munich85521 Germany Department of Infrastructure Engineering University of Melbourne ParkvilleVIC Australia Intelligent Control Laboratory PLA Rocket Force University of Engineering Xi’an710025 China Institute of Methodologies for Environmental Analysis National Research Council Tito85050 Italy School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China

Hyperspectral Image Classification (HSC) presents significant challenges owing to the high dimensionality and intricate nature of Hyperspectral (HS) data. While traditional Machine Learning (TML) approaches have demonstrated effectiveness, they often encounter substantial obstacles in real-world applications, including the variability of optimal feature sets, subjectivity in human-driven design, inherent biases, and methodological limitations. Specifically, TML suffers from the curse of dimensionality, difficulties in feature selection and extraction, insufficient consideration of spatial information, limited robustness against noise, scalability issues, and inadequate adaptability to complex data distributions. In recent years, Deep Learning (DL) techniques have emerged as robust solutions to address these challenges. This survey offers a comprehensive overview of current trends and future prospects in HSC, emphasizing advancements from DL models to the increasing adoption of Transformer and Mamba Model architectures. We systematically review key concepts, methodologies, and state-of-the-art approaches in DL for HSC. Furthermore, we investigate the potential of Transformer-based models and the Mamba Model in HSC, detailing their advantages and challenges. Emerging trends in HSC are explored, including in-depth discussions on Explainable AI and Interoperability concepts, alongside Diffusion Models for image denoising, feature extraction, and image fusion. To substantiate the efficacy of various conventional DL models, Transformers, and the Mamba Model, comprehensive experimental results were conducted on three HS datasets, yielding notable accuracies: 99.94% on Pavia University, 99.41% on Indian Pines, and 99.97% on the University of Houston dataset. Additionally, we identify several open challenges and pertinent research questions in the field of HSC. Finally, we outline future research directions and potential applications aimed at enhancing the accuracy and effic

关键词： Convolutional neural networks

A Brief Review of Explainable Artificial Intelligence in Healthcare

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sadeghi, Zahra Alizadehsani, Roohallah Cifci, Mehmet Akif Kausar, Samina Rehman, Rizwan Mahanta, Priyakshi Bora, Pranjal Kumar Almasri, Ammar Alkhawaldeh, Rami S. Hussain, Sadiq Alatas, Bilal Shoeibi, Afshin Moosaei, Hossein Hladík, Milan Nahavandi, Saeid Pardalos, Panos M. Institute for Big Data Analytics Faculty of Computer Science Dalhousie University Canada Deakin University Geelong Australia The Institute of Computer Technology Tu Wien University Vienna1040 Austria University of Kotli Azad Jammu and Kashmir Azad Kashmir Kotli Pakistan Centre for Computer Science and Applications Dibrugarh University Assam India Department of Management Information Sys Al-Balqa Applied University Salt19117 Jordan Department of Computer Information Systems The University of Jordan Aqaba77110 Jordan Examination Branch Dibrugarh University Assam Dibrugarh India Department of Software Eng. Firat University Elazig23100 Turkey Data Science and Computational Intelligence Institute University of Granada Spain Department of Informatics Faculty of Science Jan Evangelista Purkyně University in Ústí nad Labem Czech Republic Department of Applied Mathematics School of Computer Science Faculty of Mathematics and Physics Charles University Prague Czech Republic Harvard Paulson School of Engineering and Applied Sciences Harvard University AllstonMA02134 United States Center for Applied Optimization Department of Industrial and Systems Engineering University of Florida Gainesville32611 United States

XAI refers to the techniques and methods for building AI applications which assist end users to interpret output and predictions of AI models. Black box AI applications in high-stakes decision-making situations, such as medical domain have increased the demand for transparency and explainability since wrong predictions may have severe consequences. Model explainability and interpretability are vital successful deployment of AI models in healthcare practices. AI applications' underlying reasoning needs to be transparent to clinicians in order to gain their trust. This paper presents a systematic review of XAI aspects and challenges in the healthcare domain. The primary goals of this study are to review various XAI methods, their challenges, and related machine learning models in healthcare. The methods are discussed under six categories: Features-oriented methods, global methods, concept models, surrogate models, local pixel-based methods, and human-centric methods. Most importantly, the paper explores XAI role in healthcare problems to clarify its necessity in safety-critical applications. The paper intends to establish a comprehensive understanding of XAI-related applications in the healthcare field by reviewing the related experimental results. To facilitate future research for filling research gaps, the importance of XAI models from different viewpoints and their limitations are investigated. © 2023, CC BY-NC-ND.

关键词： Decision making

Interventional Contrastive Learning with Meta Semantic Regularizer

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Qiang, Wenwen Li, Jiangmeng Zheng, Changwen Su, Bing Xiong, Hui Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Guangdong China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Guangzhou China Department of Computer Science & Engineering The Hong Kong University of Science and Technology Hong Kong

Contrastive learning (CL)-based self-supervised learning models learn visual representations in a pairwise manner. Although the prevailing CL model has achieved great progress, in this paper, we uncover an ever-overlooked phenomenon: When the CL model is trained with full images, the performance tested in full images is better than that in foreground areas;when the CL model is trained with foreground areas, the performance tested in full images is worse than that in foreground areas. This observation reveals that backgrounds in images may interfere with the model learning semantic information and their influence has not been fully eliminated. To tackle this issue, we build a Structural Causal Model (SCM) to model the background as a confounder. We propose a backdoor adjustment-based regularization method, namely Interventional Contrastive Learning with Meta Semantic Regularizer (ICL-MSR), to perform causal intervention towards the proposed SCM. ICL-MSR can be incorporated into any existing CL methods to alleviate background distractions from representation learning. Theoretically, we prove that ICL-MSR achieves a tighter error bound. Empirically, our experiments on multiple benchmark datasets demonstrate that ICL-MSR is able to improve the performances of different state-of-the-art CL methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

A heterogeneous group CNN for image super-resolution

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tian, Chunwei Zhang, Yanning Zuo, Wangmeng Lin, Chia-Wen Zhang, David Yuan, Yixuan The School of Software Northwestern Polytechnical University Shaanxi Xi’an710129 China The National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an710129 China The School of Computer Science Northwestern Polytechnical University The National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an710129 China The School of Computer Science and Technology Harbin Institute of Technology Heilongjiang Harbin150001 China The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu Taiwan Guangdong Shenzhen518172 China The Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China The Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong

Convolutional neural networks (CNNs) have obtained remarkable performance via deep architectures. However, these CNNs often achieve poor robustness for image superresolution (SR) under complex scenes. In this paper, we present a heterogeneous group SR CNN (HGSRCNN) via leveraging structure information of different types to obtain a high-quality image. Specifically, each heterogeneous group block (HGB) of HGSRCNN uses a heterogeneous architecture containing a symmetric group convolutional block and a complementary convolutional block in a parallel way to enhance internal and external relations of different channels for facilitating richer low-frequency structure information of different types. To prevent appearance of obtained redundant features, a refinement block with signal enhancements in a serial way is designed to filter useless information. To prevent loss of original information, a multi-level enhancement mechanism guides a CNN to achieve a symmetric architecture for promoting expressive ability of HGSRCNN. Besides, a parallel up-sampling mechanism is developed to train a blind SR model. Extensive experiments illustrate that the proposed HGSRCNN has obtained excellent SR performance in terms of both quantitative and qualitative analysis. Codes can be accessed at https://***/hellloxiaotian/HGSRCNN. © 2022, CC BY-NC-SA.

关键词： Convolutional neural networks

Inconsistency-aware uncertainty estimation for semi-supervised medical image segmentation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Shi, Yinghuan Zhang, Jian Ling, Tong Lu, Jiwen Zheng, Yefeng Yu, Qian Qi, Lei Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University China National Institute of Healthcare Data Science Nanjing University China Department of Automation Tsinghua University China Tencent Jarvis Lab China School of Data and Computer Science Shandong Women’s University China School of Computer Science and Engineering Southeast University Nanjing211189 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210046 China

In semi-supervised medical image segmentation, most previous works draw on the common assumption that higher entropy means higher uncertainty. In this paper, we investigate a novel method of estimating uncertainty. We observe that, when assigned different misclassification costs in a certain degree, if the segmentation result of a pixel becomes inconsistent, this pixel shows a relative uncertainty in its segmentation. Therefore, we present a new semi-supervised segmentation model, namely, conservative-radical network (CoraNet in short) based on our uncertainty estimation and separate self-training strategy. In particular, our CoraNet model consists of three major components: a conservative-radical module (CRM), a certain region segmentation network (C-SN), and an uncertain region segmentation network (UC-SN) that could be alternatively trained in an end-to-end manner. We have extensively evaluated our method on various segmentation tasks with publicly available benchmark datasets, including CT pancreas, MR endocardium, and MR multi-structures segmentation on the ACDC dataset. Compared with the current state of the art, our CoraNet has demonstrated superior performance. In addition, we have also analyzed its connection with and difference from conventional methods of uncertainty estimation in semi-supervised medical image segmentation. Copyright © 2021, The Authors. All rights reserved.

关键词： Pixels

Reproducibility Assessment of Magnetic Resonance Spectroscopy of Pregenual Anterior Cingulate Cortex across Sessions and Vendors via the Cloud Computing Platform CloudBrain-MRS

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Runhan Lin, Meijin Chen, Jianshu Lin, Liangjie Wang, Jiazheng Li, Xiaoqing Wang, Jianhua Huang, Xu Qian, Ling Liu, Shaoxing Long, Yuan Guo, Di Qu, Xiaobo Han, Haiwei National Institute for Data Science in Health and Medicine Xiamen University Xiamen361102 China College of Ocean & Earth Sciences Xiamen University Xiamen361102 China Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance Xiamen University Xiamen361102 China Department of Electronic Science Xiamen University Xiamen361102 China Clinical and Technical Support Philips Healthcare Beijing100016 China School of Economics and Management Xiamen University of Technology Xiamen361024 China Department of Radiology The First Hospital Affiliated to Xiamen University Xiamen361003 China Software Technology Company Limited Suzhou215163 China School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China

Given the need to elucidate the mechanisms underlying illnesses and their treatment, as well as the lack of harmonization of acquisition and post-processing protocols among different magnetic resonance system vendors, this work is to determine if metabolite concentrations obtained from different sessions, machine models and even different vendors of 3 T scanners can be highly reproducible and be pooled for diagnostic analysis, which is very valuable for the research of rare diseases. Participants underwent magnetic resonance imaging (MRI) scanning once on two separate days within one week (one session per day, each session including two proton magnetic resonance spectroscopy (1H-MRS) scans with no more than a 5-minute interval between scans (no off-bed activity)) on each machine. were analyzed for reliability of within- and between sessions using the coefficient of variation (CV) and intraclass correlation coefficient (ICC), and for reproducibility of across the machines using correlation coefficient. As for within- and between- session, all CV values for a group of all the first or second scans of a session, or for a session were almost below 20%, and most of the ICCs for metabolites range from moderate (0.4≤ICC © 2025, CC BY.

关键词： Magnetic resonance imaging

Developing Traﬃc Congestion Detection Model Using Deep Learning Approach: A Case Study of Addis Ababa City Road

学校读者我要写书评

暂无评论

Research Square

Research Square 2020年

作者： Dursa, Bedada Bekele Tune, Kula Kekeba Department of Software Engineering Big Data and HPC CoE Addis Ababa Science and Technology University Addis Ababa Ethiopia

The traffic system is one of the core requirements of a civilized world and the development of the country depends on it in many aspects. In Ethiopia, the number of vehicles and pedestrians is increasing at a high rate from time to time. Excessive numbers of traffic on roads and improper control of traffic create traffic congestion. Uncontrolled traffic congestion hinders the transportation of goods and commuters from place to place and increases the volume of carbon emitted into the air. It can also either hampers or stagnates schedule, business, and commerce. Many images and video processing approaches have been researched in the literature on how to detect traffic congestion. One such approach is that of using background and foreground subtraction, convolutional neural network, and Average frame difference and deep learning method used to detect traffic congestion from different video sources. From the review one-stage object detector identified as the best methods to detect traffic congestion with acceptable accuracy and speed. In this study one-stage object detectors are used to detect traffic congestion from recorded video. data is collected from different video footage and frames extracted from videos to prepare a dataset for the thesis. The extracted frames were labeled manually as congested and uncongested. To train, the models pre-trained weights were used. YOLOV3 and YOLOV5 model used for experimentation. Accuracy and speed metrics used to evaluate the performance of the models. A YOLOV3 model achieved 41.6 FPS and 68.6 % mAP on a testing dataset. © 2020, CC BY.

关键词： Traffic congestion

Automated Amharic Hate Speech Posts and Comments Detection Model Using Recurrent Neural Network

学校读者我要写书评

暂无评论

Research Square

Research Square 2020年

作者： Tesfaye, Surafel Getachew Tune, Kula Kekeba Department of Software Engineering Big Data and HPC CoE Addis Ababa Science and Technology University Addis Ababa Ethiopia

During the last few years, social activities over the internet especially on social media platforms increased drastically, but unfortunately, social networks have also become the place for hate speech proliferation by which most people’s social lives are disturbed because of hate speech posts and conflicts triggered by those posts. Studies confirm that online hate speech has different offline consequences. Even though there are a lot of researches on automated hate speech detection most of them are for other language and there is a scarcity of labeled data to apply automated analysis and detection methods on Amharic dataset. Therefore the research on automatic detection of hate speech posts attracted our attention. As a solution to those problems, this research aimed to prepare a labeled huge Amharic dataset by collecting posts and comments from selected Facebook pages of activists that participated actively. Those Facebook data sets are labeled manually as hate and free based on the guidelines given from researcher and pre-processed by applying data cleaning and normalization techniques. In this research the recurrent neural network models for automated hate speech posts detection from Amharic posts on Facebook is developed by using Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) with word n-grams for feature extraction and word2vec to represent each unique word by vector representation. The experiment conducted on those two models by using 80% of the data set for training and 10% for validation to train the model and to select the best hyper-parameters combination for automated hate speech posts detection. The remaining 10% of the dataset used for testing the model after training. As a result LSTM based RNN of Batch size 128, and learning rate 0.001 with RMSProp optimizer and 0.5 dropout achieves an accuracy of 97.9% to detect posts as hate speech or free by training with 100 epochs. Which is assured by testing the models using models performance test

关键词： Long short-term memory