论文标题
基于自我相似矩阵的CNN过滤器修剪
Self Similarity Matrix based CNN Filter Pruning
论文作者
论文摘要
近年来，大多数深度学习解决方案都是针对移动设备部署的。这使得需要开发轻质模型。另一个解决方案是优化和修剪常规深度学习模型。在本文中，我们在2D CNN过滤器中计算出的自相似性矩阵（SSM）的帮助下解决了CNN模型的问题。我们提出了两种新型算法，以排名和修剪冗余过滤器，从而为输出提供了相似的激活图。我们方法的关键特征之一是训练模型后不需要填充。培训和修剪过程同时完成。我们在两个最受欢迎的CNN模型上基准测试方法 - Resnet和VGG，并在CIFAR -10数据集上记录其性能。
In recent years, most of the deep learning solutions are targeted to be deployed in mobile devices. This makes the need for development of lightweight models all the more imminent. Another solution is to optimize and prune regular deep learning models. In this paper, we tackle the problem of CNN model pruning with the help of Self-Similarity Matrix (SSM) computed from the 2D CNN filters. We propose two novel algorithms to rank and prune redundant filters which contribute similar activation maps to the output. One of the key features of our method is that there is no need of finetuning after training the model. Both the training and pruning process is completed simultaneously. We benchmark our method on two of the most popular CNN models - ResNet and VGG and record their performance on the CIFAR-10 dataset.
