30 citations · 48 across the 6 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.LG2020★ 9 cited
Overinterpretation reveals image classification model pathologies
Brandon Carter, Siddhartha Jain, Jonas Mueller +1
Image classifiers are typically scored on their test set accuracy, but high accuracy can mask a subtle type of model failure. We find that high scoring convolutional neural network…
cs.LG2020★ 2 cited
Information Condensing Active Learning
Siddhartha Jain, Ge Liu, David Gifford
We introduce Information Condensing Active Learning (ICAL), a batch mode model agnostic Active Learning (AL) method targeted at Deep Bayesian Active Learning that focuses on acquir…