Traditional deep neural networks typically use end-to-end backpropagation,
which often places a big burden on GPU memory. Another promising training
method is local learning, which involves splitting the network into blocks and
training them in parallel with the help of an auxiliary network. Local learning
has been widely studied and applied to image classification tasks, and its
performance is comparable to that of end-to-end method. However, different
image tasks often rely on different feature representations, which is difficult
for typical auxiliary networks to adapt to. To solve this problem, we propose
the construction method of Global-Local Collaborative Auxiliary Network
(GLCAN), which provides a macroscopic design approach for auxiliary networks.
This is the first demonstration that local learning methods can be successfully
applied to other tasks such as object detection and super-resolution. GLCAN not
only saves a lot of GPU memory, but also has comparable performance to an
end-to-end approach on data sets for multiple different tasks.

传统的深度神经网络通常使用端到端的反向传播方法，在 GPU 内存上往往产生很大的负担。另一种有前途的训练方法是局部学习，它将网络分为多个块，并借助辅助网络并行训练它们。局部学习已被广泛研究和应用于图像分类任务中，并且其性能与端到端方法相当。然而，不同的图像任务通常依赖于不同的特征表示，这对于典型的辅助网络而言是困难的。为了解决这个问题，我们提出了全局 - 局部协作辅助网络（GLCAN）的构建方法，为辅助网络提供了宏观设计方法。这是局部学习方法首次成功应用于目标检测和超分辨率等其他任务的示范。GLCAN 不仅节省大量 GPU 内存，而且在多个不同任务的数据集上具有与端到端方法相当的性能。