logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

Self-supervised video object segmentation via pseudo label rectification

delete2025-07-01
delete0
PRE
AI
P
Pinxue Guo
W
Wei Zhang *
F
Fan, Jianping
Z
Zhang, Wenqiang
DOI：10.1016/j.patcog.2025.111428delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
本文提出了一种新颖的自监督视频对象分割（VOS）框架，该框架包含孪生编码器和双向解码器。孪生编码器通过视觉-语义空间中的交叉注意力提取多级特征，并为每个像素生成伪标签。此类孪生编码器通过着色任务进行学习，无需任何带标签的视频数据。双向解码器接收编码器不同层的特征并输出细化的分割掩码。此类双向解码器通过伪标签进行训练，同时伪标签通过双向解码器的相互学习得到校正。通过最小化双向解码器的输出变化，使得伪标签与真实标签之间的差距减小。在具有挑战性的DAVIS-2017和YouTube-VOS数据集上的实验结果证明了我们提出方法的有效性。
Keyword:
Video object segmentation
Self-supervised learning
Pseudo label learning

期刊

Pattern Recognition 封面图
Pattern Recognition
IF:
7.6
论文数:
1.3W
被引数:
4.5W

机构

暂无机构信息
引用论文

引用论文

Self-supervised learning of scene flow with occlusion handling through feature masking
errPATTERN RECOGNITION
IF7.6
err2023-07-01
err2
PREAI
errXiang, Xuezhi; Abdein, Rokia; Lv, Ning; Yang, Jie
err分享
err收藏
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion
err2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2021-06-01
err0
errOAAI
errHo Kei Cheng; Yu-Wing Tai; Chi-Keung Tang
err分享
err收藏
Saliency-Aware Video Object Segmentation
errIEEE Transactions on Pattern Analysis and Machine Intelligence
IF0
err2018-01-01
err0
PREAI
errWenguan Wang; Jianbing Shen; Ruigang Yang; Fatih Porikli
err分享
err收藏
Video Object Segmentation-based Visual Servo Control and Object Depth Estimation on a Mobile Robot
err2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
IF0
err2020-03-01
err0
errOAAI
errBrent A. Griffin; Victoria Florence; Jason J. Corso
err分享
err收藏
Efficient Video Object Segmentation via Network Modulation
err2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
IF0
err2018-06-01
err0
errOAAI
errLinjie Yang; Yanran Wang; Xuehan Xiong; Jianchao Yang; Aggelos K. Katsaggelos
err分享
err收藏
Space-Time Memory Networks for Video Object Segmentation With User Guidance
errIEEE Transactions on Pattern Analysis and Machine Intelligence
IF0
err2022-01-01
err0
PREAI
errSeoung Wug Oh; Joon-Young Lee; Ning Xu; Seon Joo Kim
err分享
err收藏
Memory Aggregation Networks for Efficient Interactive Video Object Segmentation
err2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2020-06-01
err0
errOAAI
errJiaxu Miao; Yunchao Wei; Yi Yang
err分享
err收藏
Cross-frame feature-saliency mutual reinforcing for weakly supervised video salient object detection
errPATTERN RECOGNITION
IF7.6
err2024-06-01
err0
PREAI
errWang, Jian; Yu, Siyue; Zhang, Bingfeng; Zhao, Xinqiao; Garcia-Fernandez, Angel F.; Lim, Eng Gee; Xiao, Jimin
err分享
err收藏
Motion-Guided Cascaded Refinement Network for Video Object Segmentation
errIEEE Transactions on Pattern Analysis and Machine Intelligence
IF0
err2020-08-01
err0
PREAI
errPing Hu; Gang Wang; Xiangfei Kong; Jason Kuen; Yap-Peng Tan
err分享
err收藏
A Survey on Deep Learning Technique for Video Segmentation
errIEEE Transactions on Pattern Analysis and Machine Intelligence
IF0
err2023-06-01
err0
errOAAI
errTianfei Zhou; Fatih Porikli; David J. Crandall; Luc Van Gool; Wenguan Wang
err分享
err收藏
学者 查看更多内容