Distilling portable Generative Adversarial Networks for Image Translation
Despite Generative Adversarial Networks (GANs) have been widely used in various image-to-image translation tasks, they can be hardly applied on mobile devices due to their heavy computation and storage cost. Traditional network compression methods focus on visually recognition tasks, but never deal with generation tasks. Inspired by knowledge distillation, a student generator of fewer parameters is trained by inheriting the low-level and high-level information from the original heavy teacher generator. To promote the capability of student generator, we include a student discriminator to measure the distances between real images, and images generated by student and teacher generators. An adversarial learning process is therefore established to optimize student generator and student discriminator. Qualitative and quantitative analysis by conducting experiments on benchmark datasets demonstrate that the proposed method can learn portable generative models with strong performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Image-to-Image TranslationKnowledge DistillationTranslationSimilar Papers 제목 키워드 기반
Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation
Remarkable achievements have been attained with Generative Adversarial Networks (GANs) in image-to-image translation. However, due to a tremendous amount of parameters, state-of-the-art GANs usually suffer from low effic…
Image-to-Image TranslationKnowledge DistillationTranslationMulti-Modality Image Inpainting using Generative Adversarial Networks
Deep learning techniques, especially Generative Adversarial Networks (GANs) have significantly improved image inpainting and image-to-image translation tasks over the past few years. To the best of our knowledge, the pro…
Image InpaintingImage-to-Image TranslationTranslationSemi-Supervised Image-to-Image Translation
Image-to-image translation is a long-established and a difficult problem in computer vision. In this paper we propose an adversarial based model for image-to-image translation. The regular deep neural-network based metho…
Generative Adversarial NetworkImage SegmentationImage-to-Image TranslationMultimodal Unsupervised Image-To-Image Translation+4Not All Regions are Worthy to be Distilled: Region-aware Knowledge Distillation Towards 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 intolerant memory and computatio…
AllContrastive LearningImage-to-Image TranslationKnowledge Distillation+1Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge
Text-conditioned image generation models have recently achieved astonishing image quality and alignment results. Consequently, they are employed in a fast-growing number of applications. Since they are highly data-driven…
Image Generation