Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Marsden, Robert A."'
In deep learning, maintaining model robustness against distribution shifts is critical. This work explores a broad range of possibilities to adapt vision-language foundation models at test-time, with a particular emphasis on CLIP and its variants. Th
Externí odkaz:
http://arxiv.org/abs/2405.14977
Since distribution shifts are likely to occur after a model's deployment and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model during test-time, leveraging the current test data. In real
Externí odkaz:
http://arxiv.org/abs/2401.00989
Since distribution shifts are likely to occur during test-time and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model after deployment, leveraging the current test data. Clearly, a method
Externí odkaz:
http://arxiv.org/abs/2306.00650
Since experiencing domain shifts during test-time is inevitable in practice, test-time adaption (TTA) continues to adapt the model after deployment. Recently, the area of continual and gradual test-time adaptation (TTA) emerged. In contrast to standa
Externí odkaz:
http://arxiv.org/abs/2211.13081
Experiencing domain shifts during test-time is nearly inevitable in practice and likely results in a severe performance degradation. To overcome this issue, test-time adaptation continues to update the initial source model during deployment. A promis
Externí odkaz:
http://arxiv.org/abs/2208.07736
In recent years, there has been tremendous progress in the field of semantic segmentation. However, one remaining challenging problem is that segmentation models do not generalize to unseen domains. To overcome this problem, one either has to label l
Externí odkaz:
http://arxiv.org/abs/2208.06507
Autor:
Eskandar, George, Marsden, Robert A., Pandiyan, Pavithran, Döbler, Mario, Guirguis, Karim, Yang, Bin
Integrating different representations from complementary sensing modalities is crucial for robust scene interpretation in autonomous driving. While deep learning architectures that fuse vision and range data for 2D object detection have thrived in re
Externí odkaz:
http://arxiv.org/abs/2203.03568
Deep convolutional neural networks have considerably improved state-of-the-art results for semantic segmentation. Nevertheless, even modern architectures lack the ability to generalize well to a test dataset that originates from a different domain. T
Externí odkaz:
http://arxiv.org/abs/2105.02001
Publikováno v:
Il Capitale Culturale: Studies on the Value of Cultural Heritage; 2023 Supplement, p167-184, 18p
