Uncertainty-Aware Contrastive Distillation for Incremental Semantic Segmentation

Author:

Yang Guanglei1ORCID,Fini Enrico2ORCID,Xu Dan3ORCID,Rota Paolo2ORCID,Ding Mingli1ORCID,Nabi Moin4,Alameda-Pineda Xavier5ORCID,Ricci Elisa2ORCID

Affiliation:

1. School of Instrument Science and Engineering, Harbin Institute of Technology (HIT), Harbin, China

2. Department of Information Engineering and Computer Science, University of Trento, Trento, TN, Italy

3. Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong

4. SAP AI Research, Berlin, Germany

5. Perception Group, INRIA, Le Chesnay-Rocquencourt, France

Funder

China Scholarship Council

H2020 EU Projects SPRING and AI4Media

Fondazione Cassa Di Risparmio Di Trento E Rovereto

Deep Learning Lab of the ProM Facility

European Commission

European Institute of Innovation & Technology

ARN

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Applied Mathematics,Artificial Intelligence,Computational Theory and Mathematics,Computer Vision and Pattern Recognition,Software

Reference67 articles.

1. Continual learning: A comparative study on how to defy forgetting in classification tasks;de lange,2019

2. Contrastive learning of general-purpose audio representations;saeed,2020

3. Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem

4. Contrastive Self-Supervised Learning for Commonsense Reasoning

5. Overcoming catastrophic forgetting in neural networks;kirkpatrick;Proc Nat Acad Sci USA,2017

Cited by 25 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. ADRNet-S*: Asymmetric depth registration network via contrastive knowledge distillation for RGB-D mirror segmentation;Information Fusion;2024-08

2. Uncertainty Modeling for Group Re-Identification;International Journal of Computer Vision;2024-03-01

3. Contrastive Correlation Preserving Replay for Online Continual Learning;IEEE Transactions on Circuits and Systems for Video Technology;2024-01

4. Layer-Specific Knowledge Distillation for Class Incremental Semantic Segmentation;IEEE Transactions on Image Processing;2024

5. Morphology-Guided Network via Knowledge Distillation for RGB-D Mirror Segmentation;IEEE Transactions on Intelligent Transportation Systems;2024

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