用学生判别器提升生成模型压缩效果，让小模型也能高效超分。
SDAKD: Student Discriminator Assisted Knowledge Distillation for Super-Resolution Generative Adversarial Networks
- 引入学生判别器缓解师生模型能力不匹配问题。
- 在两个超分GAN上均超越现有压缩方法性能。
- 适合资源受限设备部署的生成模型轻量化研究者。
生成对抗网络（GAN）在图像超分辨率等生成任务中表现优异，但计算开销大，难以在资源受限设备上部署。知识蒸馏是压缩GAN的有前景方向，但因学生生成器与教师判别器之间存在能力差距，训练小型学生生成器仍具挑战。本文提出学生判别器辅助的知识蒸馏方法（SDAKD），通过引入学生判别器缓解此能力不匹配问题。SDAKD采用三阶段训练策略，并在后两个阶段融合改进的特征图蒸馏方法。我们在两个高性能超分GAN模型GCFSR和Real-ESRGAN上评估了该方法，实验表明其在多个指标上持续优于基线及当前最先进蒸馏方法。论文接受后将公开源代码。
原文摘要 · Abstract (English)
Generative Adversarial Networks (GANs) achieve excellent performance in generative tasks, such as image super-resolution, but their computational requirements make difficult their deployment on resource-constrained devices. While knowledge distillation is a promising research direction for GAN compression, effectively training a smaller student generator is challenging due to the capacity mismatch between the student generator and the teacher discriminator. In this work, we propose Student Discriminator Assisted Knowledge Distillation (SDAKD), a novel GAN distillation methodology that introduces a student discriminator to mitigate this capacity mismatch. SDAKD follows a three-stage training strategy, and integrates an adapted feature map distillation approach in its last two training stages. We evaluated SDAKD on two well-performing super-resolution GANs, GCFSR and Real-ESRGAN. Our experiments demonstrate consistent improvements over the baselines and SOTA GAN knowledge distillation methods. The SDAKD source code will be made openly available upon acceptance of the paper.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。