Traditional machine learning, mainly supervised learning, follows the assumptions of closed-
world learning, ie, for each testing class, a training class is available. However, such …

Classic supervised learning makes the closed-world assumption that the classes seen in
testing must have appeared in training. However, this assumption is often violated in real …

As science attempts to close the gap between man and machine by building systems
capable of learning, we must embrace the importance of the unknown. The ability to …

With the of advent rich classification models and high computational power visual
recognition systems have found many operational applications. Recognition in the real …

In real-world classification tasks, it is difficult to collect training samples from all possible
categories of the environment. Therefore, when an instance of an unseen class appears in …

In real-world recognition/classification tasks, limited by various objective factors, it is usually
difficult to collect training samples to exhaust all classes when training a recognizer or …

Semi-supervised learning (SSL) is one of the dominant approaches to address the
annotation bottleneck of supervised learning. Recent SSL methods can effectively leverage …

Open-set classification is a problem of handling'unknown'classes that are not contained in
the training dataset, whereas traditional classifiers assume that only known classes appear …

Conventional machine learning studies generally assume close-environment scenarios
where important factors of the learning process hold invariant. With the great success of …

We present a conceptually new and flexible method for multi-class open set classification.
Unlike previous methods where unknown classes are inferred with respect to the feature or …