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

• Main Authors: Bruintjes, Robert-Jan, Lengyel, Attila, Rios, Marcos Baptista, Kayhan, Osman Semih, van Gemert, Jan
• Format: Journal Article
• Language: English
• Published: 05-03-2021
• Subjects: Computer Science - Computer Vision and Pattern Recognition
• DOI: 10.48550/arxiv.2103.03768

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.