Search Results for author:
Found 4 papers, 1 papers with code
Multi-Sample Dropout for Accelerated Training and Better Generalization
The additional computation cost due to the duplicated operations is not significant for deep convolutional networks because most of the computation time is consumed in the convolution layers before the dropout layer, which are not duplicated.
Data Augmentation by Pairing Samples for Images Classification
This simple data augmentation technique significantly improved classification accuracy for all the tested datasets; for example, the top-1 error rate was reduced from 33. 5% to 29. 0% for the ILSVRC 2012 dataset with GoogLeNet and from 8. 22% to 6. 93% in the CIFAR-10 dataset.
Fast and Accurate Inference with Adaptive Ensemble Prediction for Deep Networks
One obvious drawback of the ensembling technique is its higher execution cost during inference.% If we average 100 local predictions, the execution cost will be 100 times as high as the cost without the ensemble.
Adaptive Ensemble Prediction for Deep Neural Networks based on Confidence Level
In this paper, we first describe our insights on the relationship between the probability of prediction and the effect of ensembling with current deep neural networks; ensembling does not help mispredictions for inputs predicted with a high probability even when there is a non-negligible number of mispredicted inputs.
