论文标题
有效的图像到图像翻译的区域感知知识蒸馏
Region-aware Knowledge Distillation for Efficient Image-to-Image Translation
论文作者
论文摘要
图像到图像翻译的最新进展见证了生成对抗网络（GAN）的成功。但是，gans通常包含大量参数，这会导致不宽容的内存和计算消耗，并限制其在边缘设备上的部署。为了解决这个问题，提出了知识蒸馏，以将知识从繁琐的教师模型转移到有效的学生模型。但是，大多数以前的知识蒸馏方法都是为图像分类而设计的，并导致图像到图像翻译的性能有限。在本文中，我们提出了区域感知的知识蒸馏Reko来压缩图像到图像翻译模型。首先，Reko自适应地找到了带有注意模块的图像中的关键区域。然后，通过贴片对比度学习来最大程度地提高这些关键地区的学生和教师之间的共同信息。在九个数据集上使用八种比较方法的实验证明了Reko对成对和未配对的图像到图像翻译的实质性有效性。例如，我们的7.08倍压缩和6.80倍加速的自行车学生的表现分别以1.33和1.04的FID得分，分别在Zebra和Zebra和Zebra上胜过马。代码将在Github上发布。
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 computation consumption and limit their deployment on edge devices. To address this issue, knowledge distillation is proposed to transfer the knowledge from a cumbersome teacher model to an efficient student model. However, most previous knowledge distillation methods are designed for image classification and lead to limited performance in image-to-image translation. In this paper, we propose Region-aware Knowledge Distillation ReKo to compress image-to-image translation models. Firstly, ReKo adaptively finds the crucial regions in the images with an attention module. Then, patch-wise contrastive learning is adopted to maximize the mutual information between students and teachers in these crucial regions. Experiments with eight comparison methods on nine datasets demonstrate the substantial effectiveness of ReKo on both paired and unpaired image-to-image translation. For instance, our 7.08X compressed and 6.80X accelerated CycleGAN student outperforms its teacher by 1.33 and 1.04 FID scores on Horse to Zebra and Zebra to Horse, respectively. Codes will be released on GitHub.
