检索结果-内蒙古大学图书馆

NTIRE 2023 Challenge on Image Super-Resolution (×4): Methods and Results

学校读者我要写书评

暂无评论

NTIRE 2023 Challenge on Image Super-Resolution (×4): Method...

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Zhang, Yulun Zhang, Kai Chen, Zheng Li, Yawei Timofte, Radu Zhang, Junpei Zhang, Kexin Peng, Rui Ma, Yanbiao Jiao, Licheng Huang, Huaibo Zhou, Xiaoqiang Ai, Yuang He, Ran Qiu, Yajun Zhu, Qiang Li, Pengfei Li, Qianhui Zhu, Shuyuan Zhang, Dafeng Li, Jia Wang, Fan Li, Chunmiao Kim, TaeHyung Kil, Jungkeong Kim, Eon Yu, Yeonseung Lee, Beomyeol Lee, Subin Lim, Seokjae Chae, Somi Choi, Heungjun Huang, ZhiKai Chen, YiChung Chiang, YuanChun Yang, HaoHsiang Chen, WeiTing Chang, HuaEn Chen, I-Hsiang Hsieh, ChiaHsuan Kuo, SyYen Choi, Ui-Jin Conde, Marcos V. Khowaja, Sunder Ali Yoon, Jiseok Lee, Ik Hyun Gendy, Garas Sabor, Nabil Hou, Jingchao He, Guanghui Zhang, Zhao Li, Baiang Zheng, Huan Zhao, Suiyi Gao, Yangcheng Wei, Yanyan Ren, Jiahuan Wei, Jiayu Li, Yanfeng Sun, Jia Cheng, Zhanyi Li, Zhiyuan Yao, Xu Wang, Xinyi Li, Danxu Cui, Xuan Cao, Jun Li, Cheng Zheng, Jianbin Sarvaiya, Anjali Prajapati, Kalpesh Patra, Ratnadeep Barik, Pragnesh Rathod, Chaitanya Upla, Kishor Raja, Kiran Ramachandra, Raghavendra Busch, Christoph Computer Vision Lab Eth Zurich Switzerland Shanghai Jiao Tong University China University of Würzburg Germany Xidian University China Mais&cripac Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China University of Science and Technology of China China Beijing Institute of Technology China School of Information Science and Technology ShanghaiTech University China School of Information and Communication Engineering University of Electronic Science and Technology of China China China Lotte Data Communication Company Seoul Korea Republic of Graduate Institute of Electronics Engineering National Taiwan University Taiwan Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan ServiceNow United States MegaStudyEdu Korea Republic of Computer Vision Lab Caidas University of Würzburg Germany University of Sindh Pakistan Iklab Inc. Tech University of Korea Siheung-Si Korea Republic of Micro-Nano Electronics Department Shanghai Jiao Tong University China Electrical Engineering Department Faculty of Engineering Assiut University Egypt Hefei University of Technology China Beijing Jiaotong University China South China University of Technology Guangdong Guangzhou China Sardar Vallabhbhai National Institute of Technology India Norwegian University of Science and Technology Norway

ISBN: (纸本)9798350302493

This paper reviews the NTIRE 2023 challenge on image super-resolution (×4), focusing on the proposed solutions and results. The task of image super-resolution (SR) is to generate a high-resolution (HR) output from a corresponding low-resolution (LR) input by leveraging prior information from paired LR-HR images. The aim of the challenge is to obtain a network design/solution capable to produce high-quality results with the best performance (e.g., PSNR). We want to explore how high performance we can achieve regardless of computational cost (e.g., model size and FLOPs) and data. The track of the challenge was to measure the restored HR images with the ground truth HR images on DIV2K testing dataset. The ranking of the teams is determined directly by the PSNR value. The challenge has attracted 192 registered participants, where 15 teams made valid submissions. They achieve state-of-the-art performance in single image super-resolution. © 2023 IEEE.

关键词： Statistical tests

Virtual Reality in Manufacturing Education: A Scoping Review Indicating State-of-the-Art, Benefits, and Challenges Across Domains, Levels, and Entities

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ipsita, Ananya Kaki, Ramesh Liu, Ziyi Patel, Mayank Duan, Runlin Deshpande, Lakshmi Yuan, Lin-Ping Lowell, Victoria Maharaj, Ashok Peppler, Kylie Feiner, Steven Ramani, Karthik School of Mechanical Engineering Purdue University West LafayetteIN47907 United States Department of Mechanical Engineering Birla Institute of Technology and Science Pilani Hyderabad Campus Telangana Hyderabad500078 India School of Electrical and Computer Engineering Purdue University West LafayetteIN47907 United States Learning Design and Technology Purdue University West LafayetteIN47907 United States Department of Computer Science Columbia University New YorkNY10027 United States School of Information and Computer Sciences University of California IrvineCA92697 United States School of Education University of California IrvineCA92697 United States Hong Kong University of Science and Technology Hong Kong TCS Avapresence- Spatial Intelligence Lab

To address the shortage of a skilled workforce in the U.S. manufacturing industry, immersive Virtual Reality (VR)-based training solutions hold promising potential. To effectively utilize VR to meet workforce demands, it is important to understand the role of VR in manufacturing education. Therefore, we conduct a scoping review in the field. As a first step, we used a 5W1H (What, Where, Who, When, Why, How) formula as a problem-solving approach to define a comprehensive taxonomy that can consider the role of VR from all relevant possibilities. Our taxonomy categorizes VR applications across three key aspects: (1) Domains, (2) Levels, and (3) Entities. Using a systematic literature search and analysis, we reviewed 108 research articles to find the current state, benefits, challenges, and future opportunities of VR in the field. It was found that VR has been explored in a variety of areas and provides numerous benefits to learners. Despite these benefits, its adoption in manufacturing education is limited. This review discusses the identified barriers and provides actionable insights to address them. These insights can enable the widespread usage of immersive technology to nurture and develop a workforce equipped with the skills required to excel in the evolving landscape of manufacturing. © 2025, CC BY.

关键词： Virtual environments

BrainMorph: A Foundational Keypoint Model for Robust and Flexible Brain MRI Registration

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Alan Q. Saluja, Rachit Kim, Heejong He, Xinzi Dalca, Adrian Sabuncu, Mert R. School of Electrical and Computer Engineering Cornell University Cornell Tech New YorkNY10044 United States Department of Radiology Weill Cornell Medical School New YorkNY10065 United States Computer Science and Artificial Intelligence Lab The Massachusetts Institute of Technology CambridgeMA02139 United States A.A. Martinos Center for Biomedical Imaging The Massachusetts General Hospital CharlestownMA02129 United States

We present a keypoint-based foundation model for general purpose brain MRI registration, based on the recently-proposed KeyMorph framework. Our model, called BrainMorph, serves as a tool that supports multi-modal, pairwise, and scalable groupwise registration. BrainMorph is trained on a massive dataset of over 100,000 3D volumes, skull-stripped and non-skull-stripped, from nearly 16,000 unique healthy and diseased subjects. BrainMorph is robust to large misalignments, interpretable via interrogating automatically-extracted keypoints, and enables rapid and controllable generation of many plausible transformations with different alignment types and different degrees of nonlinearity at test-time. We demonstrate the superiority of BrainMorph in solving 3D rigid, affine, and nonlinear registration on a variety of multi-modal brain MRI scans of healthy and diseased subjects, in both the pairwise and groupwise setting. In particular, we show registration accuracy and speeds that surpass current state-of-the-art methods, especially in the context of large initial misalignments and large group settings. All code and models are available at https://***/alanqrwang/brainmorph. © 2024, CC0.

关键词： Alignment

Modeling Dynamic User Preference via Dictionary Learning for Sequential Recommendation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Chao Li, Dongsheng Yan, Junchi Yang, Xiaokang School of Electronic Information and Electrical Engineering MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China Microsoft Research Asia Shanghai China School of Computer Science Fudan University Shanghai201203 China Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China

Capturing the dynamics in user preference is crucial to better predict user future behaviors because user preferences often drift over time. Many existing recommendation algorithms-including both shallow and deep ones-often model such dynamics independently, i.e., user static and dynamic preferences are not modeled under the same latent space, which makes it difficult to fuse them for recommendation. This paper considers the problem of embedding a user's sequential behavior into the latent space of user preferences, namely translating sequence to preference. To this end, we formulate the sequential recommendation task as a dictionary learning problem, which learns: 1) a shared dictionary matrix, each row of which represents a partial signal of user dynamic preferences shared across users;and 2) a posterior distribution estimator using a deep autoregressive model integrated with Gated Recurrent Unit (GRU), which can select related rows of the dictionary to represent a user's dynamic preferences conditioned on his/her past behaviors. Qualitative studies on the Netflix dataset demonstrate that the proposed method can capture the user preference drifts over time and quantitative studies on multiple real-world datasets demonstrate that the proposed method can achieve higher accuracy compared with state-of-the-art factorization and neural sequential recommendation methods. The code is available at https://***/cchao0116/S2PNM-TKDE2021. © 2022, CC BY.

关键词： Collaborative filtering

A Survey of the Self Supervised Learning Mechanisms for Vision Transformers

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Khan, Asifullah Sohail, Anabia Fiaz, Mustansar Hassan, Mehdi Afridi, Tariq Habib Marwat, Sibghat Ullah Munir, Farzeen Ali, Safdar Naseem, Hannan Zaheer, Muhammad Zaigham Ali, Kamran Sultana, Tangina Tanoli, Ziaurrehman Akhter, Naeem Pattern Recognition Lab DCIS PIEAS Nilore Islamabad45650 Pakistan PIEAS Nilore Islamabad45650 Pakistan Deep Learning Lab Center for Mathematical Sciences PIEAS Nilore Islamabad45650 Pakistan Center of Secure Cyber-Physical Security Systems Khalifa University Abu Dhabi United Arab Emirates IBM Research United States Department of Computer Science Air University Islamabad Pakistan Department of Computer Science and Engineering Kyung Hee University Global Campus 1732 Gyeonggi-do Yongin17104 Korea Republic of Department of Electrical Engineering and Automation Aalto University Finland Finnish Center of Artificial Center Finland Faculty of Engineering and Green Technology Universiti Tunku Abdul Rahman Malaysia Computer Vision Department Mohamed Bin Zayed University of Artificial Intelligence United Arab Emirates Karachi Pakistan Department of Electronics and Communication Engineering Hajee Mohammad Danesh Science and Technology University Bangladesh HiLIFE University of Helsinki Finland

Vision Transformers (ViTs) have recently demonstrated remarkable performance in computer vision tasks. However, their parameter-intensive nature and reliance on large amounts of data for effective performance have shifted the focus from traditional human-annotated labels to unsupervised learning and pretraining strategies that uncover hidden structures within the data. In response to this challenge, self-supervised learning (SSL) has emerged as a promising paradigm. SSL leverages inherent relationships within the data itself as a form of supervision, eliminating the need for manual labeling and offering a more scalable and resource-efficient alternative for model training. Given these advantages, it is imperative to explore the integration of SSL techniques with ViTs, particularly in scenarios with limited labeled data. Inspired by this evolving trend, this survey aims to systematically review SSL mechanisms tailored for ViTs. We propose a comprehensive taxonomy to classify SSL techniques based on their representations and pre-training tasks. Additionally, we discuss the motivations behind SSL, review prominent pre-training tasks, and highlight advancements and challenges in this field. Furthermore, we conduct a comparative analysis of various SSL methods designed for ViTs, evaluating their strengths, limitations, and applicability to different scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

Stochastic Sensitivity Regularized Autoencoder for Robust Feature Learning

学校读者我要写书评

暂无评论

Stochastic Sensitivity Regularized Autoencoder for Robust Fe...

IEEE International Conference on Cognitive Informatics

作者： Jianjun Zhang Ting Wang Wing W. Y. Ng Witold Pedrycz Sam Kwong School of Computer Science and Engineering South China University of Technology Guangzhou Guangdong China Department of Radiology Guangzhou First People's Hospital School of Medicine South China University of Technology Guangzhou Guangdong China Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information School of Computer Science and Engineering South China University of Technology Guangzhou Guangdong China Department of Electrical and Computer Engineering University of Alberta Edmonton Alberta Canada Department of Computer Science Hong Kong City University Hong Kong China

We present a new regularized autoencoder for robust feature learning. The regularization, implying stochastic sensitivity, is defined as the sum of entries of the absolute covariance matrix of the output perturbation at each layer of the autoencoder. The advantages of the stochastic sensitivity regularization are two-fold. Firstly, we show that the classical Frobenius norm regularization effectively enforces the network to be insensitive to input perturbation and that the Frobenius norm regularization is a special case of the proposed stochastic sensitivity regularization which enables the proposed method to train an autoencoder for robust feature learning. Secondly, we also show that the stochastic sensitivity regularization attempts to drive the network to learn a set of decorrelated feature maps which removes redundant information and thus improves generalization capabilities. These two properties enable the autoencoder to learn a set of robust and diverse feature maps. Finally, the efficacy and the robustness of the proposed regularization method are confirmed a nd quantified by comparing it against existing regularized auto encoders over a range of tasks.

关键词： Representation learning Sensitivity Perturbation methods Robustness Decorrelation Task analysis Covariance matrices

Generative Style Transfer for MRI Image Segmentation: A Case of Glioma Segmentation in Sub-Saharan Africa

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chepchirchir, Rancy Sunday, Jill Confidence, Raymond Zhang, Dong Chaudhry, Talha Anazodo, Udunna C. Muchungi, Kendi Zou, Yujing Institute of Mathematical Science Strathmore University Kenya Faculty of Science and Engineering University of Hull United Kingdom Department of Medical Engineering Technical University of Mombasa Kenya Medical Artificial Intelligence Lab Lagos Nigeria Lawson Health Research Institute LondonON Canada Department of Electrical and Computer Engineering University of British Columbia VancouverBC Canada University of Nairobi Nairobi Kenya Department of Clinical and Radiation Oncology University of Cape Town Cape Town South Africa Montreal Neurological Institute McGill University Montreal Canada Brain Mind Institute The Aga Khan University Nairobi Kenya Medical Physics Unit McGill University Montreal Canada

In Sub-Saharan Africa (SSA), the utilization of lower-quality Magnetic Resonance Imaging (MRI) technology raises questions about the applicability of machine learning (ML) methods for clinical tasks. This study aims to provide a robust deep learning-based brain tumor segmentation (BraTS) method tailored for the SSA population using a threefold approach. Firstly, the impact of domain shift from the SSA training data on model efficacy was examined, revealing no significant effect. Secondly, a comparative analysis of 3D and 2D full-resolution models using the nnU-Net framework indicates similar performance of both the models trained for 300 epochs achieving a five-fold cross-validation score of 0.93. Lastly, addressing the performance gap observed in SSA validation as opposed to the relatively larger BraTS glioma (GLI) validation set, two strategies are proposed: fine-tuning SSA cases using the GLI+SSA best-pretrained 2D fullres model at 300 epochs, and introducing a novel neural style transfer-based data augmentation technique for the SSA cases. This investigation underscores the potential of enhancing brain tumor prediction within SSA’s unique healthcare landscape. © 2025, CC BY.

关键词： Magnetic resonance imaging

DRG-Net: Interactive Joint Learning of Multi-lesion Segmentation and Classification for Diabetic Retinopathy Grading

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tusfiqur, Hasan Md Nguyen, Duy M.H. Truong, Mai T.N. Nguyen, Triet A. Nguyen, Binh T. Barz, Michael Profitlich, Hans-Jürgen Than, Ngoc T.T. Le, Ngan Xie, Pengtao Sonntag, Daniel Germany Machine Learning and Simulation Lab University of Stuttgart Germany Department of Multimedia Engineering Dongguk University Korea Republic of Department of Mathematics University of Architecture Ho Chi Minh City Viet Nam AISIA Lab University of Science VNUHCM Viet Nam Byers Eye Institute Stanford University United States Department of Computer Science and Computer Engineering University of Arkansas United States Department of Electrical and Computer Engineering University of California San Diego United States Applied Artificial Intelligence Oldenburg University Germany

Diabetic Retinopathy (DR) is a leading cause of vision loss in the world, and early DR detection is necessary to prevent vision loss and support an appropriate treatment. In this work, we leverage interactive machine learning and introduce a joint learning framework, termed DRG-Net, to effectively learn both disease grading and multi-lesion segmentation. Our DRG-Net consists of two modules: (i) DRG-AI-System to classify DR Grading, localize lesion areas and provide visual explanation and (ii) DRG-Expert-Interaction to receive feedback from user-expert and improve the DRG-AI-System. To deal with sparse data, we utilize transfer learning mechanisms to extract invariant feature representations by using Wasserstein distance and adversarial learning-based entropy minimization. Besides, we propose a novel attention strategy at both low- and high-level features to automatically select the most significant lesion information and provide explainable properties. In terms of human interaction, we further develop DRG-Net as a tool that enables expert users to correct the system’s predictions, which may then be used to update the system as a whole. Moreover, thanks to the attention mechanism and loss functions constraint between lesion features and classification features, our approach can be robust given a certain level of noise in the feedback of users. We have benchmarked DRG-Net on the two largest DR datasets, i.e., IDRID and FGADR, and compared it to various state-of-the-art deep learning networks. In addition to outperforming other SOTA approaches, DRG-Net is effectively updated using user feedback, even in a weakly-supervised manner. © 2022, CC BY.

关键词： Grading

Deep Generative Modeling for Volume Reconstruction in Cryo-Electron Microscopy

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Donnat, Claire Levy, Axel Poitevin, Frédéric Zhong, Ellen Miolane, Nina University of Chicago Department of Statistics ChicagoIL United States Stanford University Department of Electrical Engineering StanfordCA United States LCLS SLAC National Accelerator Laboratory Menlo ParkCA United States Massachusetts Institute of Technology Computer Science and Artificial Intelligence Lab BostonMA United States University of California Santa Barbara Department of Electrical & Computer Engineering Santa BarbaraCA United States

Recent breakthroughs in high-resolution imaging of biomolecules in solution with cryo-electron microscopy (cryo-EM) have unlocked new doors for the reconstruction of molecular volumes, thereby promising further advances in biology, chemistry, and pharmacological research. Recent next-generation volume reconstruction algorithms that combine generative modeling with end-to-end unsupervised deep learning techniques have shown promising preliminary results, but still face considerable technical and theoretical hurdles when applied to experimental cryo-EM images. In light of the proliferation of such methods, we propose here a critical review of recent advances in the field of deep generative modeling for cryo-EM volume reconstruction. The present review aims to (i) unify and compare these new methods using a consistent statistical framework, (ii) present them using a terminology familiar to machine learning researchers and computational biologists with no specific background in cryo-EM, and (iii) provide the necessary perspective on current advances to highlight their relative strengths and weaknesses, along with outstanding bottlenecks and avenues for improvements in the field. This review might also raise the interest of computer vision practitioners, as it highlights significant limits of deep generative models in low signal-to-noise regimes - therefore emphasizing a need for new theoretical and methodological developments. © 2022, CC BY.

关键词： Signal to noise ratio