Unseen Class Discovery in Open-world Classification
This addresses the challenge of identifying novel classes in open-world classification, which is incremental as it builds on existing methods for class discovery.
The paper tackles the problem of discovering hidden unseen classes in open-world classification by proposing a joint model that uses a sub-model to determine if pairs of examples belong to the same or different classes, enabling clustering of rejected examples, with experimental results indicating high promise.
This paper concerns open-world classification, where the classifier not only needs to classify test examples into seen classes that have appeared in training but also reject examples from unseen or novel classes that have not appeared in training. Specifically, this paper focuses on discovering the hidden unseen classes of the rejected examples. Clearly, without prior knowledge this is difficult. However, we do have the data from the seen training classes, which can tell us what kind of similarity/difference is expected for examples from the same class or from different classes. It is reasonable to assume that this knowledge can be transferred to the rejected examples and used to discover the hidden unseen classes in them. This paper aims to solve this problem. It first proposes a joint open classification model with a sub-model for classifying whether a pair of examples belongs to the same or different classes. This sub-model can serve as a distance function for clustering to discover the hidden classes of the rejected examples. Experimental results show that the proposed model is highly promising.