VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges. (arXiv:2201.08625v1 [cs.CV])

Web: http://arxiv.org/abs/2201.08625

The second edition of the "VIPriors: Visual Inductive Priors for
Data-Efficient Deep Learning" challenges featured five data-impaired
challenges, where models are trained from scratch on a reduced number of
training samples for various key computer vision tasks. To encourage new and
creative ideas on incorporating relevant inductive biases to improve the data
efficiency of deep learning models, we prohibited the use of pre-trained
checkpoints and other transfer learning techniques. The provided baselines are
outperformed by a large margin in all …

arxiv cv data deep deep learning learning