Deep learning models are usually developed and tested under the implicit assumption that the training and test data are drawn independently and identically distributed (IID) from the same distribution. Overlooking out-of-distribution (OOD) images can result in poor performance in unseen or adverse viewing conditions, which is common in real-world scenarios.

This competition aims to tackle typical computer vision tasks (i.e. Multi-class Classification, Object Detection, ...) on OOD images which follows a different distribution than the training images.

Submission Information

Our workshop invites submissions for two tracks:

Track 1: A codalab challenge on OOD generalization in classification, detection and 3D pose estimation. The winners and runner-ups in each category will be invited to contribute to a special issue of IJCV (International Journal of Computer Vision) and will share a prize pool of 10,000 USD.

Check the challenge page for more informations.

Track 2: A regular paper submission track. We invite submissions of long and short papers on the topic of out-of-distribution generalization. The topics include but are not limited to:
  • Improving generalization of computer vision systems in OOD scenarios
  • Research at the intersection of biological and machine vision
  • Generative causal models for image analysis
  • Domain generalization
  • Novel architectures with robustness to occlusion, viewpoint and other real-world domain shifts
  • Domain adaptation techniques for robust vision system in the real world
  • Datasets for evaluating model robustness
Check the Call for Papers page for more informations.

Organizing Committee

Sponsor


Please contact ood-cv-challenge@googlegroups.com if you have any questions.