7th Workshop on Transferring and Adapting Source Knowledge in Computer Vision and 4th VisDA Challenge Call for Papers

7th Workshop on Transferring and Adapting Source Knowledge in Computer
Vision & 4th VisDA Challenge

In conjunction with European Conference on Computer Vision (ECCV) 2020
23 August 2020, Glasgow, UK

Workshop website: https://sites.google.com/view/task-cv2020/home
VisDA challenge website: http://ai.bu.edu/visda-2020/

This is the 7th annual workshop that brings together computer vision
researchers interested in domain adaptation and knowledge transfer

A key ingredient of the recent successes of computer vision methods is
the availability of large sets of annotated data. However, collecting
them is prohibitive in many real applications and it is natural to
search for an alternative source of knowledge that needs to be
transferred or adapted to provide sufficient learning support. Our
workshop aims to bring together researchers in various sub-areas of
Transfer Learning (TL) and Domain Adaptation (DA) for computer vision.


** TL/DA learning methods for challenging paradigms like unsupervised,
incremental, open set, universal, online and federated learning

** TL/DA CNN architectures with new adaptation techniques, fine-tuning
strategies, regularization approaches, weights transfer solutions etc.

** TL/DA focusing on specific computer vision tasks (e.g., image
classification, object detection, semantic segmentation, retrieval,
tracking, etc.)  and applications (biomedical, robotics, multimedia,
autonomous driving, etc.)

** TL/DA methods working at feature and pixel (generative) level as
well as jointly applied with other learning paradigms such as
reinforcement learning

** DA in case of sensor differences (e.g., low-vs-high resolution,
power spectrum sensitivity, different RGB/Depth modalities) and
compression schemes

** Datasets and protocols for evaluating TL/DA methods

** Going beyond TL/DA towards Domain Generalization (DG)

** Multi-Task, Zero- One- and Few-Shot Learning

This is not a closed list, we welcome other interesting and relevant
research for TASK-CV.

Submission deadline: July 10th, 2020
Author notification: July 26th, 2020
Camera-ready: August 15th, 2020

The contributions will consist in Extended Abstracts (EA) of 4 pages
(including references)

As tradition we will have a best paper award supported by our sponsors.


This year the VisDA Challenge brings on board a new task, domain
adaptive pedestrian re-identification. More challenging and practical
settings are set, characterized by a synthetic-to-real domain
adaptation procedure.

** May 1: training/validation data release; evaluation server open

** Jun 25: test data release

** Jul 25: final test result submission

** Team registration is open until July 25.

Tatiana Tommasi (Politecnico di Torino, Italy)
Antonio M. Lopez (CVC & UAB, Spain)
David Vazquez (Element AI, Canada)
Gabriela Csurka (Naver Labs Europe, France)
Kate Saenko (Boston University, USA)
Liang Zheng (Australian National University, Australia)
Xingchao Peng (Boston University, USA)
Weijian Deng (Australian National University, Australia)