Deep neural networks (DNNs) typically have a single exit point that makes predictions by running the entire stack of neural layers. Since not all inputs require the same amount of computation to reach a confident prediction, recent research has focused on incorporating multiple ”exits” into the conventional DNN architecture. Early-exit DNNs are multi-exit neural networks that attach many side branches to the conventional DNN, enabling inference to stop early at intermediate points. This approach offers several advantages, including speeding up the inference process, mitigating the vanishing gradients problems, reducing overfitting and overthinking tendencies. It also supports DNN partitioning across devices and is ideal for multi-tier computation platforms such as edge computing. This paper decomposes the early-exit DNN architecture and reviews the recent advances in the field. The study explores its benefits, designs, training strategies, and adaptive inference mechanisms. Various design challenges, application scenarios, and future directions are also extensively discussed.

中文翻译：

---

早期退出深度神经网络 - 综合调查


深度神经网络 （DNN） 通常只有一个出口点，该出口点通过运行整个神经层堆栈来进行预测。由于并非所有输入都需要相同的计算量才能获得可靠的预测，因此最近的研究重点是将多个 “出口” 整合到传统的 DNN 架构中。提前退出 DNN 是多退出神经网络，它将许多侧分支附加到传统 DNN，使推理能够在中间点提前停止。这种方法具有多个优点，包括加快推理过程、缓解梯度消失问题、减少过拟合和过度思考倾向。它还支持跨设备的 DNN 分区，是边缘计算等多层计算平台的理想选择。本文分解了早期退出 DNN 架构，并回顾了该领域的最新进展。该研究探讨了它的好处、设计、训练策略和自适应推理机制。此外，还广泛讨论了各种设计挑战、应用场景和未来方向。