MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation

Author:

Miles Roy1,Yucel Mehmet Kerim1,Manganelli Bruno1,Saà-Garriga Albert1

Affiliation:

1. Samsung Research,UK

Publisher

IEEE

Reference71 articles.

1. Sstvos: Sparse spatiotem-poral transformers for video object segmentation;duke;CVPR,0

2. Efficient Regional Memory Network for Video Object Segmentation

3. SegFlow: Joint Learning for Video Object Segmentation and Optical Flow

4. Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time;wortsman;ICML,2022

5. Born Again Neural Networks;furlanello;ICML,2018

Cited by 14 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Scalable Video Object Segmentation With Identification Mechanism;IEEE Transactions on Pattern Analysis and Machine Intelligence;2024-09

2. Structural Transformer with Region Strip Attention for Video Object Segmentation;Neurocomputing;2024-09

3. DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics;2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA);2024-06-29

4. RSKD: Enhanced medical image segmentation via multi-layer, rank-sensitive knowledge distillation in Vision Transformer models;Knowledge-Based Systems;2024-06

5. Strengthening attention: knowledge distillation via cross-layer feature fusion for image classification;International Journal of Multimedia Information Retrieval;2024-05-02

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3