ood-cv.org - OOD-CV

home > domains > ood-cv.org

Example domain paragraphs

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.

The dataset can be accessed at https://bzhao.me/OOD-CV

Links to ood-cv.org (14)

• bzhao.me Bingchen Zhao
• kaihan.org Kai Han
• jiahaoplus.github.io About me - Jiahao Wang
• wufeim.github.io Wufei Ma
• laos-y.github.io Siwei Yang
• hankai.org Kai Han
• kaiyi.me Kai Yi’s Homepage
• visailab.github.io Visual AI Lab
• arnike.github.io Nikita Araslanov | Home
• k-han.github.io Kai Han
• wlin-at.github.io Wei Lin
• olvrhhn.github.io Oliver Hahn
• langnico.github.io About - Nico Lang
• arturjssln.github.io Artur Jesslen | University of Freiburg