论文标题
ppcd-gan：用于大规模有条件gans压缩的渐进修剪和类感知的蒸馏
PPCD-GAN: Progressive Pruning and Class-Aware Distillation for Large-Scale Conditional GANs Compression
论文作者
论文摘要
我们通过利用大规模有条件生成对抗网络（GAN）压缩的新型挑战性任务来推动神经网络压缩研究。为此，我们提出了逐渐收缩的GAN（PPCD-GAN），通过引入渐进式修剪残留块（PP-RES）和类感知的蒸馏。 PP-RES是常规残差块的扩展，其中每个卷积层之后是一个可学习的掩码层，随着训练的进行，可以逐步修剪修剪网络参数。另一方面，班级感知的蒸馏可以通过通过启发性的注意图从训练有素的教师模型转移巨大的知识来增强训练的稳定性。我们以端到端的方式同时培训修剪和蒸馏过程。训练后，所有冗余参数以及掩模层都会被丢弃，在保留性能的同时产生更轻的网络。我们全面说明，在Imagenet 128x128数据集上，PPCD-GAN针对最先进的工具降低了5.2倍（81％）参数，同时保持更好的性能。
We push forward neural network compression research by exploiting a novel challenging task of large-scale conditional generative adversarial networks (GANs) compression. To this end, we propose a gradually shrinking GAN (PPCD-GAN) by introducing progressive pruning residual block (PP-Res) and class-aware distillation. The PP-Res is an extension of the conventional residual block where each convolutional layer is followed by a learnable mask layer to progressively prune network parameters as training proceeds. The class-aware distillation, on the other hand, enhances the stability of training by transferring immense knowledge from a well-trained teacher model through instructive attention maps. We train the pruning and distillation processes simultaneously on a well-known GAN architecture in an end-to-end manner. After training, all redundant parameters as well as the mask layers are discarded, yielding a lighter network while retaining the performance. We comprehensively illustrate, on ImageNet 128x128 dataset, PPCD-GAN reduces up to 5.2x (81%) parameters against state-of-the-arts while keeping better performance.
