QuickNets: Saving Training and Preventing Overconfidence in Early-Exit Neural Architectures

25 December 2022

Papers citing "QuickNets: Saving Training and Preventing Overconfidence in Early-Exit Neural Architectures"

3 / 3 papers shown

Title
Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning Arian Bakhtiarnia Qi Zhang Alexandros Iosifidis 28 12 0 21 Apr 2021
Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems Shohei Enomoto Takeharu Eda UQCV 46 17 0 15 Apr 2021
Densely Connected Convolutional Networks Gao Huang Zhuang Liu L. V. D. van der Maaten Kilian Q. Weinberger PINN 3DV 264 36,371 0 25 Aug 2016