Timezone: »

 
Poster
Combining Human Predictions with Model Probabilities via Confusion Matrices and Calibration
Gavin Kerrigan · Padhraic Smyth · Mark Steyvers

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @
in Poster Session 6 »

An increasingly common use case for machine learning models is augmenting the abilities of human decision makers. For classification tasks where neither the human nor model are perfectly accurate, a key step in obtaining high performance is combining their individual predictions in a manner that leverages their relative strengths. In this work, we develop a set of algorithms that combine the probabilistic output of a model with the class-level output of a human. We show theoretically that the accuracy of our combination model is driven not only by the individual human and model accuracies, but also by the model's confidence. Empirical results on image classification with CIFAR-10 and a subset of ImageNet demonstrate that such human-model combinations consistently have higher accuracies than the model or human alone, and that the parameters of the combination method can be estimated effectively with as few as ten labeled datapoints.

Keywords: Machine Learning · Vision

Author Information

Gavin Kerrigan (UC Irvine)
Padhraic Smyth (University of California, Irvine)
Mark Steyvers (UC Irvine)

More from the Same Authors