February 24th, 2026 
Daniela Lopez de Luise Call for Papers: The Fifth Workshop on Federated Learning for Computer Vision (FedVision 2026) @ CVPR 2026
Overview:
The growing shift from centralized clouds to edge devices is reshaping AI. Federated Learning (FL) enables large-scale, privacy-preserving intelligence at the edge, offering unique opportunities and challenges for computer vision—where data are rich in semantics and privacy-sensitive. Building on four successful editions at CVPR 2022–2025, FedVision-2026 expands its focus to foundation-model adaptation, personalized and efficient edge learning, and trustworthy visual intelligence. This workshop fosters collaboration across academia, industry, and open-source communities to define the next frontier of distributed visual learning.
Topics of Interest:
We welcome papers on, but not limited to:
- Foundation-Model-Centric FL: Knowledge distillation, federated transfer learning, prompt tuning for vision–language models, and optimization for training/adapting foundation models in FL.
- Algorithms and Systems: Device- and data-heterogeneous FL, communication and resource efficiency, privacy-preserving optimization, label-efficient/self-supervised learning, neural architecture search, lifelong/federated domain adaptation, model compression, gradient sparsification, and edge deployment.
- Applications and Benchmarks: FL for scene understanding, face recognition, object detection, image segmentation, action recognition, medical imaging, novel datasets/benchmarks, and open-source FL frameworks (e.g., FedML, Flower, OpenFL).
- Trust, Fairness & Security: Privacy leakage and defenses, model/data poisoning attacks and robust defenses, fairness, interpretability, machine unlearning, and ethical/societal implications of visual data federation.
Important Dates:
- Paper Submission Deadline: March 7, 2026 (11:59 PM PST)
- Notification: March 20, 2026 (11:59 PM PST)
- Camera-Ready: April 6, 2026 (11:59 PM PST)
Accepted papers will be published in conjunction with CVPR 2026 proceedings and must follow the CVPR 2026 paper format.
- Author Kit: https://github.com/cvpr-org/author-kit/releases
- Submission Site: https://cmt3.research.microsoft.com/User/Login?ReturnUrl=%2FFedVision2026
Organizers:
- Chen Chen, Associate Professor, Center for Research in Computer Vision, Institute of Artificial Intelligence, University of Central Florida, Orlando, FL, USA, chen.chen@crcv.ucf.edu (lead organizer)
- Guangyu Sun, Ph.D. Candidate, Center for Research in Computer Vision, University of Central Florida, Orlando, FL, USA, guangyu@ucf.edu
- Nathalie Baracaldo, Research Staff Member, IBM Almaden Research Center, San Jose, CA, USA, baracald@us.ibm.com
- Victor Zhu, Sr. Manager of Research, Axon AI, USA, vzhu@axon.com
- Nicholas Lane, Professor, University of Cambridge, Cambridge, UK, ndl32@cam.ac.uk
- Yang Liu, Associate Professor, HK Polytechnic University, China, yang-veronica.liu@polyu.edu.hk
- Mahdi Morafah, Postdoctoral Researcher, The Wharton School, University of Pennsylvania, USA, mmorafah@wharton.upenn.edu
- Aritra Dutta, Assistant Professor, University of Central Florida, USA, aritra.dutta@ucf.edu
- Zhishuai Guo, Assistant Professor, Northern Illinois University, USA, zguo@niu.edu
For any questions, please contact Dr. Chen Chen at chen.chen@ucf.edu.
Posted in