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

Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking.

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

Unleashing the Power of Text-to-Image Diffusion Models for Category-Agnostic Pose Estimation.

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

Early Temporal Dynamics of Gonadal Development and Sexually Dimorphic Gene Expression During Sex Differentiation in Mandarin Fish (Siniperca chuatsi).

Marine biotechnology (New York, N.Y.)·2025
Same author

Self-Supervised Video Representation Learning by Video Incoherence Detection.

IEEE transactions on cybernetics·2023
Same author

Decoding a Percolation Phase Transition of Water at ∼330 K with a Nanoparticle Ruler.

The journal of physical chemistry letters·2020
Same author

Fast MPEG-CDVS Encoder With GPU-CPU Hybrid Computing.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2018
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

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

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

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

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

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

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

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

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

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

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
查看所有相关文章

相关实验视频

Updated: Sep 13, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

523

重播大师:自动抽样选择和有效的内存利用,用于持续的语义细分.

Lanyun Zhu, Tianrun Chen, Jianxiong Yin

    IEEE transactions on pattern analysis and machine intelligence
    |July 31, 2025
    PubMed
    概括
    此摘要是机器生成的。

    本研究引入了一种用于持续语义细分 (CSS) 的新重复方法,该方法使用强化学习自动选择最佳记忆样本. 这种方法有效地解决了阶级不平衡,并改善了重复训练,实现了最先进的结果.

    更多相关视频

    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

    2.9K
    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
    12:08

    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

    Published on: August 13, 2014

    24.7K

    相关实验视频

    Last Updated: Sep 13, 2025

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    523
    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

    2.9K
    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
    12:08

    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

    Published on: August 13, 2014

    24.7K

    科学领域:

    • 计算机视觉 计算机视觉
    • 机器学习 机器学习

    背景情况:

    • 持续语义细分 (CSS) 在逐渐引入的类上训练模型.
    • 灾难性遗忘是CSS的一个关键挑战,通常通过使用内存缓冲器的重播方法来解决.
    • 现有的重播方法在最佳样本选择和有效利用方面扎,并且经常忽视类不平衡.

    研究的目的:

    • 为持续语义分割 (CSS) 开发一种基于重复的新型管道.
    • 解决现有的重播方法内内存样本选择和利用的局限性.
    • 为了减轻与有限内存重播策略固有的类失衡问题.

    主要方法:

    • 一个强化学习框架,具有新的状态表示和一个双阶段的自动记忆样本选择的行动方案.
    • 一个专家机制和一个双阶段的培训方法来管理重播期间的类不平衡.
    • 将这些组件集成到CSS的新的基于重播的管道中.

    主要成果:

    • 拟议的方法在Pascal VOC 2012和ADE20K数据集上实现了最先进的 (SOTA) 性能.
    • 在持续语义细分中,与之前的先进方法相比,已经显著改进.
    • 验证了自动抽样选择的有效性和改进了内存利用率.

    结论:

    • 开发的基于重播的管道有效地通过优化内存样本选择和利用来增强连续语义分割.
    • 这种新的方法成功地解决了灾难性的遗忘和阶级不平衡问题.
    • 这项工作在持续语义细分的重复策略中取得了重大进展.