TASK-CV 2017

This would be the 4th annual workshop that brings together computer vision researchers interested in domain adaptation and knowledge transfer techniques. New this year would be the proposed Domain Adaptation Challenge, see below.

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

Topics

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

  • TL/DA learning methods for challenging paradigms like unsupervised, and incremental or on-line learning.
  • TL/DA focusing on specific visual features, models or learning algorithms.
  • TL/DA jointly applied with other learning paradigms such as reinforcement learning.
  • TL/DA in the era of deep neural networks (e.g., CNNs), adaptation effects of fine-tuning, regularization techniques, transfer of architectures and weights, etc.
  • TL/DA 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 methods.
  • Working frameworks with appropriate CV-oriented datasets and evaluation protocols to assess TL/DA methods.
  • Transferring knowledge across modalities (e.g., learning from 3D data for recognizing 2D data, and heterogeneous transfer learning)
  • 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.
  • Datasets and protocols for evaluating TL/DA methods.


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

Domain Adaptation Challenge

This year we are pleased to announce an accompanying Visual Domain Adaptation challenge. Please see  the challenge website for details, dates, and submission guidelines.

Best Paper Awards

The Best Paper award is sponsored this year by NAVER LABS Europe.
We will also have a Honourable Mention award supported by Amazon.
 

Acknowledgments

This workshop is sponsored by …. This workshop is also supported by the Spanish projects: TRA2014-57088-C2-1-R and DGT project SPIP2014-01352. With the support of the Secretary for Universities and Research of the Ministry of Economy and Knowledge of the Generalitat of Catalonia (2014-SGR-1506) and TECNIOspring with the FP7 of the EU and ACCIÓ.