An FPGA implementation of adaptive early-exit CNNs with partial reconfiguration saves computation on easy images, but the reported accuracy savings are not self-consistent.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A Novel Design of Adaptive and Hierarchical Convolutional Neural Networks using Partial Reconfiguration on FPGA
An FPGA implementation of adaptive early-exit CNNs with partial reconfiguration saves computation on easy images, but the reported accuracy savings are not self-consistent.