Content-Aware GAN Compression

  title={Content-Aware GAN Compression},
  author={Yuchen Liu and Zhixin Shu and Yijun Li and Zhe L. Lin and Federico Perazzi and S. Y. Kung},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Yuchen Liu, Zhixin Shu, S. Kung
  • Published 6 April 2021
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Generative adversarial networks (GANs), e.g., StyleGAN2, play a vital role in various image generation and synthesis tasks, yet their notoriously high computational cost hinders their efficient deployment on edge devices. Directly applying generic compression approaches yields poor results on GANs, which motivates a number of recent GAN compression works. While prior works mainly accelerate conditional GANs, e.g., pix2pix and Cycle-GAN, compressing state-of-the-art unconditional GANs has rarely… 

DGL-GAN: Discriminator Guided Learning for GAN Compression

A novel yet simple Discriminator Guided Learning approach for compressing vanilla GAN, dubbed DGL-GAN, which is valid since empirically, learning from the teacher discriminator could facilitate the performance of student GANs and achieves state-of-the-art results.

A Survey on GAN Acceleration Using Memory Compression Technique

The findings showed the superiority of knowledge distillation over pruning alone and the gaps in the research field that needs to be explored like encoding and different combination of compression techniques.

Region-aware Knowledge Distillation for Efficient Image-to-Image Translation

. Recent progress in image-to-image translation has witnessed the success of generative adversarial networks (GANs). However, GANs usually contain a huge number of parameters, which lead to

Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks

An INR-based video generator that improves the motion dynamics by manipulating the space and time coordinates differently and a motion discriminator that efficiently identifies the unnatural motions without observing the entire long frame sequences are introduced.

Mind the Gap in Distilling StyleGANs

This paper provides a comprehensive study of distilling from the popular StyleGAN-like architecture, and proposes a novel initialization strategy for the student model, which can ensure the output consistency to the maximum extent.

Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis

A spatial-temporal compression framework, Fast-Vid2Vid, which focuses on data aspects of generative models and makes the first attempt at time dimension to reduce computational resources and accelerate inference.

Cut Inner Layers: A Structured Pruning Strategy for Efficient U-Net GANs

This study conducts structured pruning on U-Net generators of conditional GANs with outperforms global pruning baselines, demonstrating the importance of properly considering where to prune for U- net generators.

InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images

This work proposes a novel self-supervised view generation training paradigm where it sample and render virtual camera trajectories, including cyclic camera paths, allowing the model to learn stable view generation from a collection of single views.

Evolving transferable neural pruning functions

This work crafts a novel design space to express high-quality and transferable pruning functions, which ensures an end-to-end evolution process where no manual modification is needed on the evolved functions for their transferability after evolution.

Distilling a Powerful Student Model via Online Knowledge Distillation

A novel method for online knowledge distillation, termed feature fusion and self-distillation (FFSD), which comprises two key components: FFSD, toward solving the above problems in a unified framework.



GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework

This work proposes the first unified optimization framework combining multiple compression means for GAN compression, dubbed GAN Slimming (GS), which 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.

GAN Compression: Efficient Architectures for Interactive Conditional GANs

A general-purpose compression framework for reducing the inference time and model size of the generator in cGANs and decouple the model training and architecture search via weight sharing is proposed.

Compressing GANs using Knowledge Distillation

Training an over-parameterized GAN followed by this proposed compression scheme provides a high quality generative model with a small number of parameters, and it is conjecture that this is partially owing to the optimization landscape of over- ParameterizedGANs which allows efficient training using alternating gradient descent.

Co-Evolutionary Compression for Unpaired Image Translation

  • Han ShuYunhe Wang Chang Xu
  • Computer Science
    2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
A novel co-evolutionary approach for reducing their memory usage and FLOPs simultaneously and synergistically optimized for investigating the most important convolution filters iteratively is developed.

Content-aware Deep Perceptual Image Compression

The proposed approach involves a saliency subnet to produce content saliency map for adaptive bit allocation, and designs different compression objectives for different image contents, where it tends to preserve more details for the regions with complex and saliency structures, and improves the perceptual quality of the background region.

Distilling portable Generative Adversarial Networks for Image Translation

Qualitative and quantitative analysis by conducting experiments on benchmark datasets demonstrate that the proposed method can learn portable generative models with strong performance.

Analyzing and Improving the Image Quality of StyleGAN

This work redesigns the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes to images, and thereby redefines the state of the art in unconditional image modeling.

Large Scale GAN Training for High Fidelity Natural Image Synthesis

It is found that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick," allowing fine control over the trade-off between sample fidelity and variety by reducing the variance of the Generator's input.

Improved Techniques for Training GANs

This work focuses on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic, and presents ImageNet samples with unprecedented resolution and shows that the methods enable the model to learn recognizable features of ImageNet classes.

GANSpace: Discovering Interpretable GAN Controls

This paper describes a simple technique to analyze Generative Adversarial Networks and create interpretable controls for image synthesis, and shows that BigGAN can be controlled with layer-wise inputs in a StyleGAN-like manner.