Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关实验视频

Updated: Jan 8, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.2K

通过自适应性注意力量子化变压器进行细粒度视觉分类.

Shishi Qiao, Shixian Li, Haiyong Zheng

    IEEE transactions on neural networks and learning systems
    |December 17, 2025
    PubMed
    概括
    此摘要是机器生成的。

    相关概念视频

    您也可能阅读

    相关文章

    通过共同作者、期刊和引用图与本文相关的文章。

    排序
    Same author

    Effects of hydrokinesitherapy on balance and walking ability for stroke survivors: update of a systematic review and meta-analysis of randomized controlled studies.

    European journal of physical and rehabilitation medicine·2026
    Same author

    Revisiting Face Forgery Detection: From Facial Representation to Forgery Detection.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same author

    Association between preoperative prognostic nutritional index and perioperative outcomes after unicompartmental knee arthroplasty for medial knee osteoarthritis: A retrospective single-center study.

    Medicine·2026
    Same author

    Yiqi Xugu HeJi restores cartilage metabolic homeostasis via AKT1-Thr473 activation in osteoarthritis.

    Phytomedicine : international journal of phytotherapy and phytopharmacology·2025
    Same author

    Dual-circularly polarized flat-top-beam transmitarray antenna with flexible energy allocations.

    Optics express·2025
    Same author

    Ensembling a Learned Volterra Polynomial with a Neural Network for Joint Nonlinear Distortions and Mismatch Errors Calibration of Time-Interleaved Pipelined ADCs.

    Sensors (Basel, Switzerland)·2025
    Same journal

    Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Self-Supervised Continuous Dynamic Graph Representation Learning via Hawkes Processes.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    cPU: Consistent Risk Estimator for Positive-Unlabeled Learning.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

    IEEE transactions on neural networks and learning systems·2026
    查看所有相关文章

    视觉变压器 (ViT) 模型可以通过自适应地选择区分特征来改进细粒度视觉分类 (FGVC). 我们的A2QTrans方法增强了注意力机制,使其专注于关键的图像区域,从而获得最先进的结果.

    科学领域:

    • 计算机视觉 计算机视觉
    • 机器学习 机器学习
    • 人工智能的人工智能

    背景情况:

    • 视觉转换器 (ViT) 在细粒度视觉分类 (FGVC) 中表现出色.
    • 现有的ViT方法经常与关注点集中在非歧视性区域的注意力扎,稀释关键信号.
    • 这就需要改进注意力机制,使FGVC更有效.

    研究的目的:

    • 为FGVC提出一个新的自适应注意力定量化变压器 (A2QTrans).
    • 通过分析和优化注意力头部行为来增强特征选择.
    • 在细粒度的视觉分类任务中实现最先进的性能.

    主要方法:

    • 引入了自适应量化选择 (AQS) 模块,通过注意力得分量化来动态选择歧视性特征.
    • 采用直通估计器 (STE) 在AQS模块内进行离散优化,从而实现端到端的培训.
    • 开发了一个背景消除 (BE) 模块,以改进对突出的对象的关注焦点,以及一个集成结果的动态混合优化 (DHO) 模块.

    主要成果:

    • 在四个具有挑战性的FGVC基准数据集中,A2QTrans表现出卓越的性能.
    • 该方法在三种ViT变体上测试时获得了最先进的 (SOTA) 结果.
    • 拟议的模块有效地过了不相关的信息,并将注意力集中在歧视性地区.

    相关实验视频

    Last Updated: Jan 8, 2026

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    2.2K

    结论:

    • 通过智能地管理注意力机制,A2QTrans为基于ViT的FGVC提供了显著的进步.
    • 该方法能够选择关键的区分特征,从而提高了分类准确性.
    • A2QTrans为增强视觉分类任务提供了一个强大的框架.