Pixmix: Dreamlike pictures comprehensively improve safety measures

D Hendrycks, A Zou, M Mazeika… - Proceedings of the …, 2022 - openaccess.thecvf.com
In real-world applications of machine learning, reliable and safe systems must consider
measures of performance beyond standard test set accuracy. These other goals include out …

A broad study of pre-training for domain generalization and adaptation

D Kim, K Wang, S Sclaroff, K Saenko - European Conference on Computer …, 2022 - Springer
Deep models must learn robust and transferable representations in order to perform well on
new domains. While domain transfer methods (eg, domain adaptation, domain …

Challenges for Monocular 6D Object Pose Estimation in Robotics

D Bauer, P Hönig, JB Weibel… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Object pose estimation is a core perception task that enables, for example, object
manipulation and scene understanding. The widely available, inexpensive and high …

Vision transformers in domain adaptation and domain generalization: a study of robustness

S Alijani, J Fayyad, H Najjaran - Neural Computing and Applications, 2024 - Springer
Deep learning models are often evaluated in scenarios where the data distribution is
different from those used in the training and validation phases. The discrepancy presents a …

Progressively select and reject pseudo-labelled samples for open-set domain adaptation

Q Wang, F Meng, TP Breckon - IEEE Transactions on Artificial …, 2024 - ieeexplore.ieee.org
Domain adaptation solves image classification problems in the target domain by taking
advantage of the labelled source data and unlabelled target data. Usually, the source and …

Learning Visual Conditioning Tokens to Correct Domain Shift for Fully Test-time Adaptation

Y Tang, S Chen, Z Kan, Y Zhang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Fully test-time adaptation aims to adapt the network model based on sequential analysis of
input samples during the inference stage to address the cross-domain performance …

Challenges for monocular 6d object pose estimation in robotics

S Thalhammer, D Bauer, P Hönig, JB Weibel… - arXiv preprint arXiv …, 2023 - arxiv.org
Object pose estimation is a core perception task that enables, for example, object grasping
and scene understanding. The widely available, inexpensive and high-resolution RGB …

Domain-Conditioned Transformer for Fully Test-time Adaptation

Y Tang, S Chen, J Jia, Y Zhang, Z He - ACM Multimedia 2024, 2024 - openreview.net
Fully test-time adaptation aims to adapt a network model online based on sequential
analysis of input samples during the inference stage. We observe that, when applying a …

Vision Transformers in Domain Adaptation and Generalization: A Study of Robustness

S Alijani, J Fayyad, H Najjaran - arXiv preprint arXiv:2404.04452, 2024 - arxiv.org
Deep learning models are often evaluated in scenarios where the data distribution is
different from those used in the training and validation phases. The discrepancy presents a …

Dual-Path Adversarial Lifting for Domain Shift Correction in Online Test-time Adaptation

Y Tang, S Chen, Z Lu, X Wang, Z He - arXiv preprint arXiv:2408.13983, 2024 - arxiv.org
Transformer-based methods have achieved remarkable success in various machine
learning tasks. How to design efficient test-time adaptation methods for transformer models …