AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2020
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917883343273984 |
|---|---|
| author | Fu, Yonggan Chen, Wuyang Wang, Haotao Li, Haoran Lin, Yingyan Celine Wang, Zhangyang |
| author_facet | Fu, Yonggan Chen, Wuyang Wang, Haotao Li, Haoran Lin, Yingyan Celine Wang, Zhangyang |
| contents | The compression of Generative Adversarial Networks (GANs) has lately drawn attention, due to the increasing demand for deploying GANs into mobile devices for numerous applications such as image translation, enhancement and editing. However, compared to the substantial efforts to compressing other deep models, the research on compressing GANs (usually the generators) remains at its infancy stage. 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 (AGD) framework. Starting with a specifically designed efficient search space, AGD performs an end-to-end discovery for new efficient generators, given the target computational resource constraints. The search is guided by the original GAN model via knowledge distillation, therefore fulfilling the compression. AGD is fully automatic, standalone (i.e., needing no trained discriminators), and generically applicable to various GAN models. We evaluate AGD in two representative GAN tasks: image translation and super resolution. Without bells and whistles, AGD yields remarkably lightweight yet more competitive compressed models, that largely outperform existing alternatives. Our codes and pretrained models are available at https://github.com/TAMU-VITA/AGD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2006_08198 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks Fu, Yonggan Chen, Wuyang Wang, Haotao Li, Haoran Lin, Yingyan Celine Wang, Zhangyang Computer Vision and Pattern Recognition Machine Learning Image and Video Processing The compression of Generative Adversarial Networks (GANs) has lately drawn attention, due to the increasing demand for deploying GANs into mobile devices for numerous applications such as image translation, enhancement and editing. However, compared to the substantial efforts to compressing other deep models, the research on compressing GANs (usually the generators) remains at its infancy stage. 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 (AGD) framework. Starting with a specifically designed efficient search space, AGD performs an end-to-end discovery for new efficient generators, given the target computational resource constraints. The search is guided by the original GAN model via knowledge distillation, therefore fulfilling the compression. AGD is fully automatic, standalone (i.e., needing no trained discriminators), and generically applicable to various GAN models. We evaluate AGD in two representative GAN tasks: image translation and super resolution. Without bells and whistles, AGD yields remarkably lightweight yet more competitive compressed models, that largely outperform existing alternatives. Our codes and pretrained models are available at https://github.com/TAMU-VITA/AGD. |
| title | AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks |
| topic | Computer Vision and Pattern Recognition Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2006.08198 |