2 Hits in 4.2 sec

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  ...  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.  ...  INTRODUCTION While Convolutional Neural Networks are becoming the state-ofthe-art algorithm in various Machine Vision tasks [1] [2] [3] , they are challenged to deal with problems of continuously increasing  ... 
arXiv:1805.08743v1 fatcat:dyalnovqhbgehm2qrohh2nyxbi

Learned 3D Shape Representations Using Fused Geometrically Augmented Images: Application to Facial Expression and Action Unit Detection [article]

Bilal Taha, Munawar Hayat, Stefano Berretti, Naoufel Werghi
2019 arXiv   pre-print
This new fused modality enables us to learn feature representations from 3D data in a highly efficient manner by simply employing standard convolutional neural networks in a transfer-learning mode.  ...  The extensive experiments conducted on the Bosphorus and BU-4DFE datasets, show that our method produces a significant boost in the performance when compared to state-of-the-art solutions  ...  The face alignment method employs a cascaded CNN to handle the self-occlusions.  ... 
arXiv:1904.04297v1 fatcat:mvki5yzbjjekte26i5rfga7n4q