Sacrificing Accuracy for Reduced Computation: Cascaded Inference Based on Softmax Confidence

We study the tradeoff between computational effort and accuracy in a cascade of deep neural networks. During inference, early termination in the cascade is controlled by confidence levels derived directly from the softmax outputs of intermediate classifiers. The advantage of early termination is that classification is performed using less computation, thus adjusting the computational effort to the complexity of the input. Moreover, dynamic modification of confidence thresholds allow one to trade accuracy for computational effort without requiring retraining. Basing of early termination on softmax classifier outputs is justified by experimentation that demonstrates an almost linear relation between confidence levels in intermediate classifiers and accuracy. Our experimentation with architectures based on ResNet obtained the following results. (i) A speedup of 1.5 that sacrifices 1.4% accuracy with respect to the CIFAR-10 test set. (ii) A speedup of 1.19 that sacrifices 0.7% accuracy with respect to the CIFAR-100 test set. (iii) A speedup of 2.16 that sacrifices 1.4% accuracy with respect to the SVHN test set.