← Search

Erik Kruus

2 accepted papers

2023

Source-Free Video Domain Adaptation With Spatial-Temporal-Historical Consistency Learning

CVPR 2023poster

Source-free domain adaptation (SFDA) is an emerging research topic that studies how to adapt a pretrained source model using unlabeled target data. It is derived from unsupervised domain adaptation but has the advantage of not requiring labeled source data to learn adaptive models. This makes it par…

2021

Towards Robustness of Deep Neural Networks via Regularization

ICCV 2021poster

Recent studies have demonstrated the vulnerability of deep neural networks against adversarial examples. Inspired by the observation that adversarial examples often lie outside the natural image data manifold and the intrinsic dimension of image data is much smaller than its pixel space dimension, w…

Cited by 18PDFcodeScholar