Federated Learning for Computer Vision (FedVision) Call for Papers


CVPR 2022 Workshop: Federated Learning for Computer Vision (FedVision)
(In conjunction with CVPR 2022, June 19, New Orleans, US)

Website: https://sites.google.com/view/fedvision
Contact: Dr. Chen Chen (chen.chen@crcv.ucf.edu)

Federated Learning (FL) has become an important privacy-preserving
paradigm in various machine learning tasks. However, the potential of
FL in computer vision applications, such as face recognition, person
re-identification, and action recognition, is far from being fully
exploited. Moreover, FL has rarely been demonstrated effectively in
advanced computer vision tasks such as object detection and image
segmentation, compared to the traditional centralized training
paradigm. This workshop aims at bringing together researchers and
practitioners with common interests in FL for computer vision and
studying the different synergistic relations in this interdisciplinary
area. The day-long event will facilitate interaction among students,
scholars, and industry professionals from around the world to discuss
future research challenges and opportunities.


Keynote speakers 

    Dr. Yiran Chen, Duke University 
    Dr. Salman Avestimehr, University of Southern California 
    Dr. Zheng Xu, Google 
    Dr. Jeffrey Byrne, CEO of Visym Labs 
    Dr. Handong Zhao, Adobe System 
    Dr. Yuejie Chi, Carnegie Mellon University 


Call for paper 

Main research topics of relevance to this workshop include, but are
not limited to:

    Novel FL models for computer vision tasks, e.g., scene
      understanding, face recognition, object detection, person
      re-identification, image segmentation, human action recognition,
      medical image processing, etc.
    Privacy-preserving machine learning for computer vision tasks 
    Personalized FL models for computer vision applications 
    Novel computer vision applications of FL and privacy-preserving machine learning 
    FL frameworks and tools designed for computer vision applications and benchmarking 
    Novel vision datasets for FL 
    Optimization algorithms for FL, particularly algorithms tolerant of data heterogeneity and resource heterogeneity 
    Approaches that scale FL to larger models, including model pruning and gradient compression techniques 
    Label efficient learning in FL, e.g., self-supervised learning, semi-supervised learning, active learning, etc. 
    Neural architecture search (NAS) for FL 
    Life-long learning in FL 
    Attacks on FL including model poisoning, data poisoning, and corresponding defenses 
    Fairness in FL 
    Federated domain adaptation 
    Privacy leakage and defense in the FL environments 
    Privacy-preserving Generative models for CV  
    FL based CV pipeline for scene understanding and visual analytics 

Submission Deadline: March 9, 2022 (11:59 PM, PST) 

Notification: March 27, 2022 (11:59 PM, PST) 

Camera-Ready: April 5, 2022 (11:59 PM, PST) 

Accepted papers will be published in conjunction with CVPR 2022
proceedings. Paper submissions will adhere to the CVPR 2022 paper
submission style, format, and length restrictions. The CVPR 2022
author kit is available:

Enter the paper submission website:

For any questions, please contact Dr. Chen Chen (chen.chen@crcv.ucf.edu)