CalexNet aligns early-exit branch training and calibration to the cascade inference distribution via weighted sampling, survivor-subset calibration, and KL distillation to the backbone, matching or exceeding baselines on CIFAR-100 and CINIC-10 accuracy-FLOPs frontiers.
The described method avoids a covariance shift caused by a difference between training and inference distributions when early exit branches are trained on the entire dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CalexNet: Soft Cascade-Aligned Training and Calibration for Lightweight Early-Exit Branches
CalexNet aligns early-exit branch training and calibration to the cascade inference distribution via weighted sampling, survivor-subset calibration, and KL distillation to the backbone, matching or exceeding baselines on CIFAR-100 and CINIC-10 accuracy-FLOPs frontiers.