276 papers with code • 16 benchmarks • 19 datasets
The idea of Domain Generalization is to learn from one or multiple training domains, to extract a domain-agnostic model which can be applied to an unseen domain
Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains.
Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers.
Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks.
We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions.
Then we propose a new dataset called ImageNet-P which enables researchers to benchmark a classifier's robustness to common perturbations.
CORAL is a "frustratingly easy" unsupervised domain adaptation method that aligns the second-order statistics of the source and target distributions with a linear transformation.