首页|Segmentation-aware image super-resolution with generative adversarial networks
Segmentation-aware image super-resolution with generative adversarial networks
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Springer Nature
Deep neural networks have greatly facilitated the research in the area of image super-resolution. Existing super-resolution networks primarily focus on optimizing visual image quality, and there has been little work considering the potential use of the super-resolved image for machine vision tasks, such as semantic segmentation. In this paper, we propose a segmentation-aware image super-resolution network, by incorporating machine-related semantic segmentation task requirement. To achieve this, we propose to generate super-resolved images by employing generative adversarial networks, where the super-resolution network functions as the generator, while the discriminator consists of the popular real/fake classification branch and an additional task branch. With this specially-designed multi-branch discriminator, segmentation task requirement is used as an added training objective provided to the generator for producing super-resolved images with segmentation awareness. Moreover, by performing alternative training between the generator and the discriminator, we dynamically enhance the capacity of task branch along with the super-resolving process, achieving generalization ability for the resulting super-resolved image. Experimental results show that, for the semantic segmentation task, our proposed method is at most 6.8 higher than competing methods in terms of mIoU score. Furthermore, our method can also generate visually better super-resolved images at the same time.
Deep learningGenerative adversarial networkImage super-resolutionSemantic segmentation
Jiliang Wang、Cancan Jin、Siwang Zhou
展开 >
Changsha Environmental Protection Vocational College, Changsha, China
College of Computer Science and Electronic Engineering, Hunan University, Changsha, China
NETL
NSTL
Springer Nature
