Machine learning draws its power from various disciplines, including computer science,
cognitive science, and statistics. Although machine learning has achieved great …

Abstract Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of
machine learning systems. For instance, in autonomous driving, we would like the driving …

Supervised learning aims to train a classifier under the assumption that training and test
data are from the same distribution. To ease the above assumption, researchers have …

Federated learning (FL) has attracted growing attentions via data-private collaborative
training on decentralized clients. However, most existing methods unrealistically assume …

Open set recognition (OSR), aiming to simultaneously classify the seen classes and identify
the unseen classes as' unknown', is essential for reliable machine learning. The key …

Recently, develo** automated video surveillance systems (VSSs) has become crucial to
ensure the security and safety of the population, especially during events involving large …

Unsupervised domain adaptation without accessing expensive annotation processes of
target data has achieved remarkable successes in semantic segmentation. However, most …

Open-world classification systems should discern out-of-distribution (OOD) data whose
labels deviate from those of in-distribution (ID) cases, motivating recent studies in OOD …

Unsupervised domain adaptation has attracted appealing academic attentions by
transferring knowledge from labeled source domain to unlabeled target domain. However …

Existing methods for open set action recognition focus on novelty detection that assumes
video clips show a single action, which is unrealistic in the real world. We propose a new …