Abstract Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence of distribution …

The goal of semantic segmentation is to segment the input image according to semantic
information and predict the semantic category of each pixel from a given label set. With the …

Rigorously testing autonomy systems is essential for making safe self-driving vehicles (SDV)
a reality. It requires one to generate safety critical scenarios beyond what can be collected …

In unsupervised domain adaptation (UDA), a model trained on source data (eg synthetic) is
adapted to target data (eg real-world) without access to target annotation. Most previous …

Test-time domain adaptation aims to adapt a source pre-trained model to a target domain
without using any source data. Existing works mainly consider the case where the target …

Test-time training adapts to a new test distribution on the fly by optimizing a model for each
test input using self-supervision. In this paper, we use masked autoencoders for this one …

As acquiring pixel-wise annotations of real-world images for semantic segmentation is a
costly process, a model can instead be trained with more accessible synthetic data and …

Test-time adaptation is a special setting of unsupervised domain adaptation where a trained
model on the source domain has to adapt to the target domain without accessing source …

We investigate the efficacy of visual prompting to adapt large-scale models in vision.
Following the recent approach from prompt tuning and adversarial reprogramming, we learn …

Unsupervised domain adaptation (UDA) aims to adapt a model trained on the source
domain (eg synthetic data) to the target domain (eg real-world data) without requiring further …