NSTL国家科技图书文献中心

1. Contrastive Learning with Synthetic Positives NSTL国家科技图书文献中心

Dewen Zeng | Yawen Wu ... - 《Computer Vision - ECCV 2024,Part XXXVII》 - European Conference on Computer Vision - 2025, - 430～447 - 共18页

摘要：Contrastive learning with the nearest neighbor has proved to be one of the most efficient self-supervised learning (SSL) techniques by utilizing the similarity of multiple instances within the same cl...

关键词： Self-supervised learning | Contrastive learning | Diffusion model

2. Efficient Harvesting Waste Heat by Zn-Ion Battery Under Thermally Regenerative Electrochemical Cycles NSTL国家科技图书文献中心

Xiaoling Sun | Hongyi Chen ... - 《Advanced Materials》 - 2025,37(12) - 1～8 - 共8页

摘要：Typical technologies that can convert waste heat into electricity include thermoelectrics, thermionic capacitors, thermo-cells, thermal charge cells, and thermally regenerative electrochemical cycles....

关键词： energy efficiency | heat harvesting | temperature coefficient of voltage | thermally regenerative electrochemical battery | thermal-to-electrical conversion efficiency | Zn-ion battery

3. Enhancing 3D Transformer Segmentation Model for Medical Image with Token-level Representation Learning NSTL国家科技图书文献中心

Xinrong Hu | Dewen Zeng ... - 《2024 IEEE International Conference on Bioinformatics and Biomedicine》 - IEEE International Conference on Bioinformatics and Biomedicine - 2024, - 3299～3302 - 共4页

摘要：In the field of medical images, although various works find Swin Transformer has promising effectiveness on pixelwise dense prediction, whether pre-training these models without using extra dataset ca...

关键词： Representation learning | Solid modeling | Three-dimensional displays | Biological system modeling | Semantic segmentation | Self-supervised learning | Predictive models | Transformers | Bioinformatics | Biomedical imaging

4. Achieving Fairness Through Channel Pruning for Dermatological Disease Diagnosis NSTL国家科技图书文献中心

Qingpeng Kong | Ching-Hao Chiu ... - 《Medical Image Computing and Computer Assisted Intervention - MICCAI 2024,Part X》 - International Conference on Medical Image Computing and Computer Assisted Intervention - 2024, - 24～34 - 共11页

摘要：Numerous studies have revealed that deep learning-based medical image classification models may exhibit bias towards specific demographic attributes, such as race, gender, and age. Existing bias mitig...

关键词： Dermatological disease diagnosis | AI fairness | Medical image analysis | Channel pruning

5. Self-Supervised On-Device Federated Learning From Unlabeled Streams NSTL国家科技图书文献中心

Jiahe Shi | Yawen Wu ... - 《IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems: A publication of the IEEE Circuits and Systems Society》 - 2023,42(12) - 4871～4882 - 共12页

摘要：The ubiquity of edge devices has led to a growing amount of unlabeled data produced at the edge. Deep learning models deployed on edge devices are required to learn from these unlabeled data to contin...

关键词： Training | Federated learning | Distributed databases | Servers | Data models | Visualization | Image edge detection | Self-supervised learning | Learning systems

6. Additional Positive Enables Better Representation Learning for Medical Images NSTL国家科技图书文献中心

Dewen Zeng | Yawen Wu ... - 《Medical Image Computing and Computer Assisted Intervention - MICCAI 2023: 26th International Conference, Vancouver, BC, Canada, October 8-12, 2023, Proceedings, Part I》 - International Conference on Medical Image Computing and Computer Assisted Intervention - 2023, - 119～129 - 共11页

摘要：This paper presents a new way to identify additional positive pairs for BYOL, a state-of-the-art (SOTA) self-supervised learning framework, to improve its representation learning ability. Unlike conve...

关键词： Self-supervised learning | Representation learning | Medical image classification

7. Maiby's Algorithm: A Two-Stage Deep Learning Approach for Murmur Detection in Mel Spectrograms for Automatic Auscultation of Congenital Heart Disease NSTL国家科技图书文献中心

Matheus Araujo | Dewen Zeng ... - 《2022 Computing in Cardiology: CinC 2022, Tampere, Finland, 4-7 September 2022, [v.1]》 - Computing in Cardiology Conference - 2022, - 1～4 - 共4页

摘要：Congenital heart disease (CHD) is a major cause of death for newborns, especially in low resources countries, due to limited access to heart specialists for timely diagnosis. As part of the George B. ...

关键词： Heart | Deep learning | Pediatrics | Sensitivity | Costs | Classification algorithms | Feedforward neural networks

8. Contrastive Learning with Temporal Correlated Medical Images: A Case Study using Lung Segmentation in Chest X-Rays NSTL国家科技图书文献中心

Dewen Zeng | John N. Kheir ... - 《2021 IEEE/ACM International Conference on Computer Aided Design: ICCAD 2021, Munich, Germany, 1-4 November 2021, [v.2]》 - IEEE/ACM International Conference on Computer Aided Design - 2021, - 776～782 - 共7页

摘要：Contrastive learning has been proved to be a promising technique for image-level representation learning from unlabeled data. Many existing works have demonstrated improved results by applying contras...

关键词： Medical image segmentation | Contrastive learning | Chest x-rays

9. Semi-supervised Contrastive Learning for Label-Efficient Medical Image Segmentation NSTL国家科技图书文献中心

Xinrong Hu | Dewen Zeng ... - 《Medical image computing and computer assisted intervention - MICCAI 2021, Part 2: 24th international conference on medical image computing and computer assisted intervention (MICCAI 2021), September 27 - October 1 2021, Strasbourg, France》 - International conference on medical image computing and computer assisted intervention - 2021, - 481～490 - 共10页

摘要：The success of deep learning methods in medical image segmentation tasks heavily depends on a large amount of labeled data to supervise the training. On the other hand, the annotation of biomedical i...

关键词： Semi-supervised learning | Contrastive learning | Semantic segmentation | Label efficient learning

10. Semi-supervised Contrastive Learning for Label-Efficient Medical Image Segmentation NSTL国家科技图书文献中心

Xinrong Hu | Dewen Zeng ... - 《Medical Image Computing and Computer Assisted Intervention - MICCAI 2021: 24th International Conference, Strasbourg, France, September 27 - October 1, 2021, Proceedings, Part II》 - International Conference on Medical Image Computing and Computer Assisted Intervention - 2021, - 481～490 - 共10页

摘要：The success of deep learning methods in medical image segmentation tasks heavily depends on a large amount of labeled data to supervise the training. On the other hand, the annotation of biomedical im...

摘要：Contrastive learning with the nearest neighbor has proved to be one of the most efficient self-supervised learning (SSL) techniques by utilizing the similarity of multiple instances within the same cl...

关键词： Self-supervised learning | Contrastive learning | Diffusion model

摘要：Typical technologies that can convert waste heat into electricity include thermoelectrics, thermionic capacitors, thermo-cells, thermal charge cells, and thermally regenerative electrochemical cycles....

关键词： energy efficiency | heat harvesting | temperature coefficient of voltage | thermally regenerative electrochemical battery | thermal-to-electrical conversion efficiency | Zn-ion battery

摘要：In the field of medical images, although various works find Swin Transformer has promising effectiveness on pixelwise dense prediction, whether pre-training these models without using extra dataset ca...

关键词： Representation learning | Solid modeling | Three-dimensional displays | Biological system modeling | Semantic segmentation | Self-supervised learning | Predictive models | Transformers | Bioinformatics | Biomedical imaging

摘要：Numerous studies have revealed that deep learning-based medical image classification models may exhibit bias towards specific demographic attributes, such as race, gender, and age. Existing bias mitig...

关键词： Dermatological disease diagnosis | AI fairness | Medical image analysis | Channel pruning

摘要：The ubiquity of edge devices has led to a growing amount of unlabeled data produced at the edge. Deep learning models deployed on edge devices are required to learn from these unlabeled data to contin...

关键词： Training | Federated learning | Distributed databases | Servers | Data models | Visualization | Image edge detection | Self-supervised learning | Learning systems

摘要：This paper presents a new way to identify additional positive pairs for BYOL, a state-of-the-art (SOTA) self-supervised learning framework, to improve its representation learning ability. Unlike conve...

关键词： Self-supervised learning | Representation learning | Medical image classification

摘要：Congenital heart disease (CHD) is a major cause of death for newborns, especially in low resources countries, due to limited access to heart specialists for timely diagnosis. As part of the George B. ...

关键词： Heart | Deep learning | Pediatrics | Sensitivity | Costs | Classification algorithms | Feedforward neural networks

摘要：Contrastive learning has been proved to be a promising technique for image-level representation learning from unlabeled data. Many existing works have demonstrated improved results by applying contras...

关键词： Medical image segmentation | Contrastive learning | Chest x-rays

摘要：The success of deep learning methods in medical image segmentation tasks heavily depends on a large amount of labeled data to supervise the training. On the other hand, the annotation of biomedical i...

关键词： Semi-supervised learning | Contrastive learning | Semantic segmentation | Label efficient learning

摘要：The success of deep learning methods in medical image segmentation tasks heavily depends on a large amount of labeled data to supervise the training. On the other hand, the annotation of biomedical im...

关键词： Semi-supervised learning | Contrastive learning | Semantic segmentation | Label efficient learning

4008-161-200 800-990-8900

国家科技图书文献中心