Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …

Small data are often used in scientific and engineering research due to the presence of
various constraints, such as time, cost, ethics, privacy, security, and technical limitations in …

Bridging thereality gap'that separates simulated robotics from experiments on hardware
could accelerate robotic research through improved data availability. This paper explores …

Deep domain adaptation has emerged as a new learning technique to address the lack of
massive amounts of labeled data. Compared to conventional methods, which learn shared …

Abstract Machine learning and data mining techniques have been used in numerous real-
world applications. An assumption of traditional machine learning methodologies is the …

Object detection typically assumes that training and test data are drawn from an identical
distribution, which, however, does not always hold in practice. Such a distribution mismatch …

Do visual tasks have a relationship, or are they unrelated? For instance, could having
surface normals simplify estimating the depth of an image? Intuition answers these …

We evaluate whether features extracted from the activation of a deep convolutional network
trained in a fully supervised fashion on a large, fixed set of object recognition tasks can be re …

Recent reports suggest that a generic supervised deep CNN model trained on a large-scale
dataset reduces, but does not remove, dataset bias on a standard benchmark. Fine-tuning …

Unlike human learning, machine learning often fails to handle changes between training
(source) and test (target) input distributions. Such domain shifts, common in practical …