activity
20222026
most citedTransferring Styles for Reduced Texture Bias and Improved Robustness in Semantic Segmentation Networks

2 citations · 3 across the 9 of their papers we have counts for

collaborators
Showing 2022Show all

1 paper · 1 filter

cs.CV2022★ 1 cited

AttEntropy: On the Generalization Ability of Supervised Semantic Segmentation Transformers to New Objects in New Domains

Krzysztof Lis, Matthias Rottmann, Annika Mütze +3

In addition to impressive performance, vision transformers have demonstrated remarkable abilities to encode information they were not trained to extract. For example, this informat…