Anonymous Model Pruning for Compressing Deep Neural Networks

Many deep neural network compression algorithms need to fine-tune on source dataset, which makes them unpractical when the source datasets are unavailable. Although data-free methods can overcome this problem, they often suffer from a huge loss of accuracy. In this paper, we propose a novel approach named Anonymous-Model Pruning (AMP), which seeks to compress the network without the source data and the accuracy can be guaranteed without too much loss. AMP compresses deep neural networks via searching pruning rate automatically and fine-tuning the compressed model under the teacher-student diagram. The key innovations are that the pruning rate is automatically determined, and the fine-tuning process is under the guidance of uncompressed network instead of labels. Even without the source dataset, compared with existing pruning methods, our proposed method can still achieve comparable accuracy with similar pruning rate. For example, for ResNet50, our AMP method only incur 0.76% loss in top-1 accuracy with 32.72% pruning rate.