Augmentation-based Domain Generalization for Semantic Segmentation

Understand

Unsupervised Domain Adaptation (UDA) and domain generalization (DG) are two research areas that aim to tackle the lack of generalization of Deep Neural Networks (DNNs) towards unseen domains.

• While UDA methods have access to unlabeled target images, domain generalization does not involve any target data and only learns generalized features from a source domain.
• Image-style randomization or augmentation is a popular approach to improve network generalization without access to the target domain.
• Complex methods are often proposed that disregard the potential of simple image augmentations for out-of-domain generalization.