Neural network uncertainty estimates correlate only weakly with human-perceived uncertainty on three vision benchmarks, and soft-label training improves that alignment, though the claimed calibration benefit is not measured in the paper.
In: Proceedings of the 32nd International Conference on Interna- tional Conference on Machine Learning - Volume 37 (2015)
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
-
Uncertainty Estimation by Human Perception versus Neural Models
Neural network uncertainty estimates correlate only weakly with human-perceived uncertainty on three vision benchmarks, and soft-label training improves that alignment, though the claimed calibration benefit is not measured in the paper.