Query by Committee Made Real

140 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Learning Algorithms for Active Learning (2017, methodology): “ing the instance whose label the model is most uncertain about, or the instance whose label is expected to maximally reduce the model’s uncertainty about labels for other instances (Gilad-Bachrach et al., 2005; Settles, 2010; Houlsby et al., 2011).”
Learning to Play with Intrinsically-Motivated Self-Aware Agents (2018, background): “In traditional active learning, an agent seeks to learn a supervised task from using little labeled data as possible, with the ability to request more labeled data if necessary (Settles, 2011; Gilad-Bachrach et al., 2005).”
Variational Adversarial Active Learning (2019, methodology): “Pool-based methods have been theoretically proven to be effective and achieve better performance than the random sampling of points [45, 14, 17].”
Learning Active Learning from Data (2017, background): “They include uncertainty sampling [32, 15, 27, 34], query-by-committee [7, 13], expected model change [27, 30, 33], expected error or variance minimization [14, 9] and information gain [10].”
What Do I Annotate Next? An Empirical Study of Active Learning for Action Localization (2018, background): “As compared to traditional active learners [27,42] where heuristics such as uncertainty sampling are used to perform the sample selection, we explore novel selection functions [25,40] that reuse knowledge from a previously existing dataset.”