Mixup applied only to the student during KD induces independent linearity acquisition that reduces overconfidence by an order of magnitude while improving accuracy, with calibration transferring separately from accuracy.
arXiv preprint arXiv:2103.13941 (2021)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Dark Knowledge: Mixup-Based Distillation for Reliable Predictions
Mixup applied only to the student during KD induces independent linearity acquisition that reduces overconfidence by an order of magnitude while improving accuracy, with calibration transferring separately from accuracy.