BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks

TL;DR

BranchyNet introduces early exit points in deep neural networks, enabling faster inference and reduced energy consumption by allowing easy-to-classify samples to exit early, while more complex samples use the full network.

Contribution

The paper proposes a novel architecture with side branch classifiers for early exiting, improving inference speed and efficiency without sacrificing accuracy.

Findings

Significant reduction in inference time across tested networks.

Maintains or improves classification accuracy.

Effective early exit strategy for real-time applications.

Abstract

Deep neural networks are state of the art methods for many learning tasks due to their ability to extract increasingly better features at each network layer. However, the improved performance of additional layers in a deep network comes at the cost of added latency and energy usage in feedforward inference. As networks continue to get deeper and larger, these costs become more prohibitive for real-time and energy-sensitive applications. To address this issue, we present BranchyNet, a novel deep network architecture that is augmented with additional side branch classifiers. The architecture allows prediction results for a large portion of test samples to exit the network early via these branches when samples can already be inferred with high confidence. BranchyNet exploits the observation that features learned at an early layer of a network may often be sufficient for the classification of many data points. For more difficult samples, which are expected less frequently, BranchyNet will use further or all network layers to provide the best likelihood of correct prediction. We study the BranchyNet architecture using several well-known networks (LeNet, AlexNet, ResNet) and datasets (MNIST, CIFAR10) and show that it can both improve accuracy and significantly reduce the inference time of the network.