We present an approach to adaptively utilize deep neural networks in order to
reduce the evaluation time on new examples without loss of accuracy. Rather
than attempting to redesign or approximate existing networks, we propose two
schemes that adaptively utilize networks. We first pose an adaptive network
evaluation scheme, where we learn a system to adaptively choose the components
of a deep network to be evaluated for each example. By allowing examples
correctly classified using early layers of the system to exit, we avoid the
computational time associated with full evaluation of the network. We extend
this to learn a network selection system that adaptively selects the network to
be evaluated for each example. We show that computational time can be
dramatically reduced by exploiting the fact that many examples can be correctly
classified using relatively efficient networks and that complex,
computationally costly networks are only necessary for a small fraction of
examples. We pose a global objective for learning an adaptive early exit or
network selection policy and solve it by reducing the policy learning problem
to a layer-by-layer weighted binary classification problem. Empirically, these
approaches yield dramatic reductions in computational cost, with up to a 2.8x
speedup on state-of-the-art networks from the ImageNet image recognition
challenge with minimal (<1%) loss of top5 accuracy.

通过自适应选取深度神经网络组件或网络进行评估，可以在不损失准确性的情况下，显著减少计算时间，例如在 ImageNet 图像识别挑战中，最多可加速 2.8 倍，并且仅有最高 5 个命中率的轻微损失。