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

CRPGAN: Learning image-to-image translation of two unpaired images by cross-attention mechanism and parallelization strategy.

PloS one·2023
Same author

Skull Sex Estimation Based on Wavelet Transform and Fourier Transform.

BioMed research international·2020
Same author

Sex Determination of Three-Dimensional Skull Based on Improved Backpropagation Neural Network.

Computational and mathematical methods in medicine·2019
Same author

Sex Determination of 3D Skull Based on a Novel Unsupervised Learning Method.

Computational and mathematical methods in medicine·2018
Same author

Fast and Robust Reconstruction for Fluorescence Molecular Tomography via <i>L</i><sub>1-2</sub> Regularization.

BioMed research international·2017
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
查看所有相关文章

相关实验视频

Updated: May 29, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

359

自主监督图像细分使用元学习和多脊柱功能融合.

Muhammad Shahroz Ajmal1, Guohua Geng1, Xiaofeng Wang1

  • 1School of Information Science and Technology, Northwest University, Xi'an, 710069, P. R. China.

International journal of neural systems
|February 4, 2025
PubMed
概括
此摘要是机器生成的。

本研究介绍了一种使用自我监督和多个特征的骨干的多脊柱少数拍摄细分 (MBFSS) 方法. 它显著提高了对未标记数据的细分性能,并尽量减少注释.

关键词:
只有几次射击.功能融合功能融合功能多个脊柱的多个脊柱.自己监督的自我监督.语义细分 语义细分 语义细分 语义细分

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

455
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K

相关实验视频

Last Updated: May 29, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

359
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

455
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K

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:

  • 短拍细分 (FSS) 减少了手动注释的需求,但对于基础类需要大量的标记数据.
  • 现有的FSS方法在一般化和依赖广泛的标记数据集方面扎.
  • 解决数据注释的高成本和时间对于实际的FSS应用至关重要.

研究的目的:

  • 提出一种新的自主监督的少数镜头细分方法 (MBFSS),尽量减少对标记数据的依赖.
  • 通过整合多个骨干网络来增强特征表示.
  • 改进模型概括,减少FSS中的注释工作.

主要方法:

  • 开发了一种多个骨干的少量冲击细分 (MBFSS) 方法.
  • 采用自主监督学习,利用无监督的突出性对未标记的数据进行伪标签.
  • 来自多个骨干 (ResNet,ResNeXt,PVT v2) 的集成功能,用于更丰富的表示.

主要成果:

  • 在PASCAL-5i和COCO-20i数据集的一次性细分中分别达到54.3%和25.1%的准确性.
  • 在一次性细分任务中表现比基准方法高13.5%和4%.
  • 证明了显著的性能增长,而标签工作几乎可以忽略不计.

结论:

  • 拟议的MBFSS方法有效地减少了在少数拍摄细分中需要手动注释的需求.
  • 整合多个骨干和自我监督学习可以提高模型的概括性和性能.
  • 这种方法为具有有限标记数据的现实世界FSS应用提供了实用解决方案.