Furthermore, it has also achievedstate-of-the-art performance incombination with recent developments inself-supervised learning methodologies as well [37,62].

Fine-tuning works [63] tominimizeE(x, y) Di[f( i;x, y)], where i isusually of g beforefine-tuning.

Efficient methods that reliably quantify a deep neural network (DNN)'s predictive uncertainty are important for industrial-scale, real-world applications, which include examples such as object recognition in autonomous driving [22], ad click prediction in online advertising [76], and intent understanding inaconversational system [84].

Segmentation of curvilinear structures such as vasculature and road networks is challenging due to relatively weak signals and complex geometry/topology.

Homomorphic encryption has recently attracted attention as a key solution to preserve privacy in machine learning applications.