arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.15366cs.CVeess.IV
收藏

基于知识蒸馏的人脸到卡通图像增量超分辨率

Face to Cartoon Incremental Super-Resolution using Knowledge Distillation

Indian Institute of Information Technology, Allahabad(印度阿拉哈巴德信息技术学院);Sorbonne Centre for Artificial Intelligence, Sorbonne University Abu Dhabi(索邦大学阿布扎比分校索邦人工智能中心)

Trinetra Devkatte, Shiv Ram Dubey, Satish Kumar Singh, Abdenour Hadid

AI总结:

针对GAN人脸超分辨率模型适配新数据的难题,提出结合知识蒸馏的人脸到卡通增量超分辨率框架ISR-KD,经CelebA预训练、iCartoonFace增量训练,可在保留原有人脸幻视能力的同时提升卡通人脸超分辨率性能。

摘要:

人脸超分辨率/幻视是一个重要的研究领域,旨在为各类应用增强低分辨率人脸图像。尽管生成对抗网络(GANs)在该领域已展现出潜力,但它们适配全新未见过数据的能力仍是一大挑战。本文针对这一问题,提出了一种面向人脸到卡通图像的、结合知识蒸馏的GAN增量超分辨率方法(ISR-KD)。该领域以往的研究尚未探究增量学习,而在新数据持续生成的实际应用场景中,增量学习至关重要。本文提出的ISR-KD旨在构建一种新型统一的人脸超分辨率框架,可适配不同设置,包括卡通人脸等不同类型的人脸以及不同的细节层级。为实现这一目标,研究团队先在CelebA数据集上预训练一个基于GAN的超分辨率网络,再在iCartoonFace数据集上进行增量训练,利用知识蒸馏在提升iCartoonFace测试集性能的同时,保留模型在CelebA测试集上的表现。我们的实验证明,知识蒸馏能够有效为GAN模型增量添加卡通人脸超分辨率能力,同时保留模型已习得的人脸幻视任务相关知识。

英文摘要:

Facial super-resolution/hallucination is an important area of research that seeks to enhance low-resolution facial images for a variety of applications. While Generative Adversarial Networks (GANs) have shown promise in this area, their ability to adapt to new, unseen data remains a challenge. This paper addresses this problem by proposing an incremental super-resolution using GANs with knowledge distillation (ISR-KD) for face to cartoon. Previous research in this area has not investigated incremental learning, which is critical for real-world applications where new data is continually being generated. The proposed ISR-KD aims to develop a novel unified framework for facial super-resolution that can handle different settings, including different types of faces such as cartoon face and various levels of detail. To achieve this, a GAN-based super-resolution network was pre-trained on the CelebA dataset and then incrementally trained on the iCartoonFace dataset, using knowledge distillation to retain performance on the CelebA test set while improving the performance on iCartoonFace test set. Our experiments demonstrate the effectiveness of knowledge distillation in incrementally adding capability to the model for cartoon face super-resolution while retaining the learned knowledge for facial hallucination tasks in GANs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑