Typical Convolutional Neural Networks (ConvNets) depend heavily on large amounts of image data and resort to an iterative optimization algorithm (e.g., SGD or Adam) to learn network parameters, which makes training very time- and resource-intensive. In this paper, we propose a new training paradigm and formulate the parameter learning of ConvNets into a prediction task: given a ConvNet architecture, we observe there exists correlations between image datasets and their corresponding optimal network parameters, and explore if we can learn a hyper-mapping between them to capture the relations, such that we can directly predict the parameters of the network for an image dataset never seen during the training phase. To do this, we put forward a new hypernetwork based model, called PudNet, which intends to learn a mapping between datasets and their corresponding network parameters, and then predicts parameters for unseen data with only a single forward propagation. Moreover, our model benefits from a series of adaptive hyper recurrent units sharing weights to capture the dependencies of parameters among different network layers. Extensive experiments demonstrate that our proposed method achieves good efficacy for unseen image datasets on two kinds of settings: Intra-dataset prediction and Inter-dataset prediction. Our PudNet can also well scale up to large-scale datasets, e.g., ImageNet-1K. It takes 8967 GPU seconds to train ResNet-18 on the ImageNet-1K using GC from scratch and obtain a top-5 accuracy of 44.65 %. However, our PudNet costs only 3.89 GPU seconds to predict the network parameters of ResNet-18 achieving comparable performance (44.92 %), more than 2,300 times faster than the traditional training paradigm.

翻译：典型的卷积神经网络（ConvNets）严重依赖大量图像数据，并采用迭代优化算法（如SGD或Adam）来学习网络参数，这使得训练过程极其耗时且耗费资源。本文提出一种新的训练范式，将ConvNet的参数学习转化为预测任务：给定一个ConvNet架构，我们观察到图像数据集与其对应的最优网络参数之间存在相关性，并探索能否学习一个超映射来捕捉这种关系，从而直接预测训练阶段未见图像数据集的网络参数。为此，我们提出一种基于超网络的新模型PudNet，旨在学习数据集与其对应网络参数之间的映射，并通过单次前向传播直接预测未见数据的参数。此外，该模型采用一系列自适应超循环单元共享权重，以捕捉不同网络层参数之间的依赖关系。大量实验表明，所提方法在两种设置（数据集内预测和数据集间预测）下对未见图像数据集均取得了良好效果。PudNet还能有效扩展至大规模数据集（如ImageNet-1K）：使用梯度累积从头训练ResNet-18需要8967 GPU秒，获得44.65%的Top-5准确率；而PudNet仅需3.89 GPU秒即可预测ResNet-18的网络参数并达到相当的性能（44.92%），比传统训练范式快2300倍以上。