9 citations · 11 across the 9 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.CV2021
Improving the Behaviour of Vision Transformers with Token-consistent Stochastic Layers
Nikola Popovic, Danda Pani Paudel, Thomas Probst +1
We introduce token-consistent stochastic layers in vision transformers, without causing any severe drop in performance. The added stochasticity improves network calibration, robust…
cs.CV2021★ 9 cited
Rethinking Global Context in Crowd Counting
Guolei Sun, Yun Liu, Thomas Probst +3
This paper investigates the role of global context for crowd counting. Specifically, a pure transformer is used to extract features with global information from overlapping image p…