This paper strives for domain generalization, where models are trained
e...
Prototype-based meta-learning has emerged as a powerful technique for
ad...
In this paper, we propose energy-based sample adaptation at test time fo...
In this paper, we focus on multi-task classification, where related
clas...
We strive to learn a model from a set of source domains that generalizes...
Domain generalization is challenging due to the domain shift and the
unc...
Crowd counting has recently attracted increasing interest in computer vi...
Crowd counting usually addressed by density estimation becomes an
increa...