VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges

Logo of the VIPriors 2020 challenges.

Abstract

We present the first edition of “VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning” challenges. We offer four data-impaired challenges, where models are trained from scratch, and we reduce the number of training samples to a fraction of the full set. Furthermore, to encourage data efficient solutions, we prohibited the use of pre-trained models and other transfer learning techniques. The majority of top ranking solutions make heavy use of data augmentation, model ensembling, and novel and efficient network architectures to achieve significant performance increases compared to the provided baselines.

Publication
ArXiv (ArXiv 2021)
Robert-Jan Bruintjes
Robert-Jan Bruintjes
PhD candidate

Interested in integrating prior knowledge into Convolutional Neural Networks to benefit data efficiency and/or robustness.

Osman Semih Kayhan
Osman Semih Kayhan
PhD Candidate

Interests include equivariant CNNs and context in object detection.

Jan van Gemert
Jan van Gemert
Associate Professor

Head of the CV Lab.

Related