GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework
arXiv:2008.11062
Abstract
Generative adversarial networks (GANs) have gained increasing popularity in various computer vision applications, and recently start to be deployed to resource-constrained mobile devices. Similar to other deep models, state-of-the-art GANs suffer from high parameter complexities. That has recently motivated the exploration of compressing GANs (usually generators). Compared to the vast literature and prevailing success in compressing deep classifiers, the study of GAN compression remains in its infancy, so far leveraging individual compression techniques instead of more sophisticated combinations. We observe that due to the notorious instability of training GANs, heuristically stacking different compression techniques will result in unsatisfactory results. To this end, we propose the first unified optimization framework combining multiple compression means for GAN compression, dubbed GAN Slimming (GS). GS seamlessly integrates three mainstream compression techniques: model distillation, channel pruning and quantization, together with the GAN minimax objective, into one unified optimization form, that can be efficiently optimized from end to end. Without bells and whistles, GS largely outperforms existing options in compressing image-to-image translation GANs. Specifically, we apply GS to compress CartoonGAN, a state-of-the-art style transfer network, by up to 47 times, with minimal visual quality degradation. Codes and pre-trained models can be found at https://github.com/TAMU-VITA/GAN-Slimming.
ECCV 2020 spotlight
References in corpus (18)
- Adam: A Method for Stochastic Optimization
- Distilling the Knowledge in a Neural Network
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices
- Trained Ternary Quantization
- Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures
- A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
- Model compression via distillation and quantization
- Unifying distillation and privileged information
- Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy
- Faster gaze prediction with dense networks and Fisher pruning
- Preserving Color in Neural Artistic Style Transfer
- AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks
- Model Compression with Adversarial Robustness: A Unified Optimization Framework
- SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation
- AdaDeep: A Usage-Driven, Automated Deep Model Compression Framework for Enabling Ubiquitous Intelligent Mobiles
- Graph-Adaptive Pruning for Efficient Inference of Convolutional Neural Networks