CascadeCNN: Pushing the performance limits of quantisation [article]

Alexandros Kouris, Stylianos I. Venieris, Christos-Savvas Bouganis
2018 arXiv   pre-print
This work presents CascadeCNN, an automated toolflow that pushes the quantisation limits of any given CNN model, to perform high-throughput inference by exploiting the computation time-accuracy trade-off. Without the need for retraining, a two-stage architecture tailored for any given FPGA device is generated, consisting of a low- and a high-precision unit. A confidence evaluation unit is employed between them to identify misclassified cases at run time and forward them to the high-precision
more » ... t or terminate computation. Experiments demonstrate that CascadeCNN achieves a performance boost of up to 55% for VGG-16 and 48% for AlexNet over the baseline design for the same resource budget and accuracy.
arXiv:1805.08743v1 fatcat:dyalnovqhbgehm2qrohh2nyxbi