论文标题
用于无数据网络量化的条件生成对抗网络的零击学习
Zero-Shot Learning of a Conditional Generative Adversarial Network for Data-Free Network Quantization
论文作者
论文摘要
我们提出了一种新的方法，用于训练有条件的生成对抗网络（CGAN），而无需使用训练数据，即CGAN（ZS-CGAN）的零射击学习。条件发生器的零射门学习只需要预先训练的判别（分类）模型，并且不需要任何培训数据。特别是，对条件发生器进行了训练，以生成标记的合成样品，其特征通过使用存储在预训练模型的批处理层中的统计数据来模仿原始训练数据。我们显示了ZS-CAN在深神经网络无数据量化中的实用性。我们实现了在Imagenet数据集上训练的Resnet和Mobilenet分类模型的最新无数据网络量化。与常规数据依赖性量化相比，使用ZS-CGAN无数据量化的准确性损失最少。
We propose a novel method for training a conditional generative adversarial network (CGAN) without the use of training data, called zero-shot learning of a CGAN (ZS-CGAN). Zero-shot learning of a conditional generator only needs a pre-trained discriminative (classification) model and does not need any training data. In particular, the conditional generator is trained to produce labeled synthetic samples whose characteristics mimic the original training data by using the statistics stored in the batch normalization layers of the pre-trained model. We show the usefulness of ZS-CGAN in data-free quantization of deep neural networks. We achieved the state-of-the-art data-free network quantization of the ResNet and MobileNet classification models trained on the ImageNet dataset. Data-free quantization using ZS-CGAN showed a minimal loss in accuracy compared to that obtained by conventional data-dependent quantization.
