For intelligent interfaces attempting to learn a user’s interests, the cost of obtaining labeled training instances is prohibitive because the user must directly label each trai...
A problem of supervised approaches for text classification is that they commonly require high-quality training data to construct an accurate classifier. Unfortunately, in many real...
Abstract. In this paper, we propose a new dynamic learning framework that requires a small amount of labeled data in the beginning, then incrementally discovers informative unlabel...
Weijun He, Xiaolei Huang, Dimitris N. Metaxas, Xia...
Similarity metrics that are learned from labeled training
data can be advantageous in terms of performance
and/or efficiency. These learned metrics can then be used
in conjuncti...
We introduce the problem of zero-data learning, where a model must generalize to classes or tasks for which no training data are available and only a description of the classes or...