Distance from a softmax prediction to the mean softmax vector of correct examples can serve as a confidence score for flagging low-confidence and out-of-distribution predictions, based on MNIST and CIFAR-10 experiments.
In: Proceedings of the International Conference on Computer Vision Theory and Applications, Lisbon, Portugal (February 2009)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Explorations of the Softmax Space: Knowing When the Neural Network Doesn't Know
Distance from a softmax prediction to the mean softmax vector of correct examples can serve as a confidence score for flagging low-confidence and out-of-distribution predictions, based on MNIST and CIFAR-10 experiments.