[visionlist] ICCV Workshop on Transferring and Adapting Source Knowledge in Computer Vision

Tatiana Tommasi tommasi.t at gmail.com
Sat Jun 29 12:28:06 -04 2019

6th workshop on Transferring and Adapting Source Knowledge in Computer
Vision and
3rd VisDA Challenge

In conjunction with International Conference on Computer Vision (ICCV) 2019
2 Novembre 2019, Seoul, Korea


This is the 6th annual workshop that brings together computer vision
researchers interested in
domain adaptation and knowledge transfer techniques.

A key ingredient of the recent successes in computer vision has been the
availability of visual
data with annotations, both for training and testing, and well-established
protocols for evaluating
the results. However, this traditional supervised learning framework is
limited when it comes to
deployment on new tasks and/or operating in new domains. In order to scale
to such situations,
we must find mechanisms to reuse the available annotations or the models
learned from them.

TASK-CV aims to bring together research in transfer learning (TL), domain
generalization (DG) and
domain adaptation  (DG) for computer vision and invites the submission of
research contributions on
the following topics:

- TL/DA/DG learning methods for challenging paradigms like unsupervised,
self-supervised, incremental,
and online learning;
- TL/DA/DG focusing on specific visual features, models or learning
- TL/DA/DG applied for procedural learning (e.g. state-action pairs,
reinforcement learning);
- TL/DA/DG in the era of convolutional neural networks (CNNs), adaptation
effects of fine-tuning,
regularization techniques, transfer of architectures and weights, etc;
- TL/DA/DG focusing on specific computer vision tasks (e.g., image
classification, object detection,
semantic segmentation, recognition, retrieval, tracking, etc.) and
applications (biomedical, robotics,
multimedia, autonomous driving, etc.);
- Comparative studies of different TL/DA/DG methods;
- Working frameworks with appropriate datasets and evaluation protocols to
assess TL/DA/DG methods;
- Transferring part representations between categories;
- Transferring tasks to new domains;
- Solving domain shift due to sensor differences (e.g., low-vs-high
resolution, power spectrum sensitivity)
and compression schemes;
- Extensions of few- and zero-shot learning approaches across domains.

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

Paper Submission: July 10th, 2019 (deadline extended!)
Notification of Acceptance: July 22nd, 2019
Camera-Ready: August 10th, 2019

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

Tatiana Tommasi, Politecnico di Torino, Italy
David Vázquez, Element AI, Canada
Kate Saenko, Boston University, USA
Ben Usman, Boston University, USA
Xingchao Peng, Boston University, USA
Judy Hoffman, Facebook AI Research, USA
Neela Kaushik, Boston University, USA
Antonio M. López, Universitat Autònoma de Barcelona (UAB) and Computer
Vision Center (CVC), Spain
Wen Li, ETH Zurich, Switzerland
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20190629/e4edf2a4/attachment.html>

More information about the visionlist mailing list