Online Multi-Granularity Distillation for GAN Compression
- URL: http://arxiv.org/abs/2108.06908v1
- Date: Mon, 16 Aug 2021 05:49:50 GMT
- Title: Online Multi-Granularity Distillation for GAN Compression
- Authors: Yuxi Ren, Jie Wu, Xuefeng Xiao, Jianchao Yang
- Abstract summary: Generative Adversarial Networks (GANs) have witnessed prevailing success in yielding outstanding images.
GANs are burdensome to deploy on resource-constrained devices due to ponderous computational costs and hulking memory usage.
We propose a novel online multi-granularity distillation scheme to obtain lightweight GANs.
- Score: 17.114017187236836
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Generative Adversarial Networks (GANs) have witnessed prevailing success in
yielding outstanding images, however, they are burdensome to deploy on
resource-constrained devices due to ponderous computational costs and hulking
memory usage. Although recent efforts on compressing GANs have acquired
remarkable results, they still exist potential model redundancies and can be
further compressed. To solve this issue, we propose a novel online
multi-granularity distillation (OMGD) scheme to obtain lightweight GANs, which
contributes to generating high-fidelity images with low computational demands.
We offer the first attempt to popularize single-stage online distillation for
GAN-oriented compression, where the progressively promoted teacher generator
helps to refine the discriminator-free based student generator. Complementary
teacher generators and network layers provide comprehensive and
multi-granularity concepts to enhance visual fidelity from diverse dimensions.
Experimental results on four benchmark datasets demonstrate that OMGD successes
to compress 40x MACs and 82.5X parameters on Pix2Pix and CycleGAN, without loss
of image quality. It reveals that OMGD provides a feasible solution for the
deployment of real-time image translation on resource-constrained devices. Our
code and models are made public at: https://github.com/bytedance/OMGD.
Related papers
- Discriminator-Cooperated Feature Map Distillation for GAN Compression [69.86835014810714]
We present an inventive discriminator-cooperated distillation, abbreviated as DCD, towards refining better feature maps from the generator.
Our DCD shows superior results compared with existing GAN compression methods.
arXiv Detail & Related papers (2022-12-29T03:50:27Z) - DGL-GAN: Discriminator Guided Learning for GAN Compression [57.6150859067392]
Generative Adversarial Networks (GANs) with high computation costs have achieved remarkable results in synthesizing high-resolution images from random noise.
We propose a novel yet simple bf Discriminator bf Guided bf Learning approach for compressing vanilla bf GAN, dubbed bf DGL-GAN.
arXiv Detail & Related papers (2021-12-13T09:24:45Z) - MFAGAN: A Compression Framework for Memory-Efficient On-Device
Super-Resolution GAN [27.346272886257335]
We propose a novel compression framework textbfMulti-scale textbfFeature textbfAggregation Net based textbfGAN (MFAGAN) for reducing the memory access cost of the generator.
MFAGAN achieves up to textbf8.3$times$ memory saving and textbf42.9$times$ computation reduction, compared with ESRGAN.
arXiv Detail & Related papers (2021-07-27T09:04:30Z) - Teachers Do More Than Teach: Compressing Image-to-Image Models [35.40756344110666]
Generative Adversarial Networks (GANs) have achieved huge success in generating high-fidelity images.
GANs suffer from low efficiency due to tremendous computational cost and bulky memory usage.
Recent efforts on compression GANs show noticeable progress in obtaining smaller generators.
arXiv Detail & Related papers (2021-03-05T04:29:34Z) - Learning Efficient GANs for Image Translation via Differentiable Masks
and co-Attention Distillation [130.30465659190773]
Generative Adversarial Networks (GANs) have been widely-used in image translation, but their high computation and storage costs impede the deployment on mobile devices.
We introduce a novel GAN compression method, termed DMAD, by proposing a Differentiable Mask and a co-Attention Distillation.
Experiments show DMAD can reduce the Multiply Accumulate Operations (MACs) of CycleGAN by 13x and that of Pix2Pix by 4x while retaining a comparable performance against the full model.
arXiv Detail & Related papers (2020-11-17T02:39:19Z) - TinyGAN: Distilling BigGAN for Conditional Image Generation [2.8072597424460466]
BigGAN has significantly improved the quality of image generation on ImageNet, but it requires a huge model, making it hard to deploy on resource-constrained devices.
We propose a black-box knowledge distillation framework for compressing GANs, which highlights a stable and efficient training process.
Given BigGAN as the teacher network, we manage to train a much smaller student network to mimic its functionality, achieving competitive performance on Inception and FID scores with the generator having $16times$ fewer parameters.
arXiv Detail & Related papers (2020-09-29T07:33:49Z) - GAN Slimming: All-in-One GAN Compression by A Unified Optimization
Framework [94.26938614206689]
We propose the first unified optimization framework combining multiple compression means for GAN compression, dubbed GAN Slimming.
We apply GS to compress CartoonGAN, a state-of-the-art style transfer network, by up to 47 times, with minimal visual quality degradation.
arXiv Detail & Related papers (2020-08-25T14:39:42Z) - AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks [98.71508718214935]
Existing GAN compression algorithms are limited to handling specific GAN architectures and losses.
Inspired by the recent success of AutoML in deep compression, we introduce AutoML to GAN compression and develop an AutoGAN-Distiller framework.
We evaluate AGD in two representative GAN tasks: image translation and super resolution.
arXiv Detail & Related papers (2020-06-15T07:56:24Z) - Blur, Noise, and Compression Robust Generative Adversarial Networks [85.68632778835253]
We propose blur, noise, and compression robust GAN (BNCR-GAN) to learn a clean image generator directly from degraded images.
Inspired by NR-GAN, BNCR-GAN uses a multiple-generator model composed of image, blur- Kernel, noise, and quality-factor generators.
We demonstrate the effectiveness of BNCR-GAN through large-scale comparative studies on CIFAR-10 and a generality analysis on FFHQ.
arXiv Detail & Related papers (2020-03-17T17:56:22Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.