arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.07604cs.CVcs.AI
收藏

基于协同蒸馏和核分解的人脸化妆传输网络压缩

Compressing Facial Makeup Transfer Networks by Collaborative Distillation and Kernel Decomposition

Chu Kochen Honors College, Zhejiang University(浙江大学竺可桢学院)

Bianjiang Yang, Zi Hui, Haoji Hu, Xinyi Hu, Lu Yu

摘要:

虽然面部化妆传输网络在生成感知上令人愉悦的化妆图像方面取得了高质量的性能,但其能力仍然受到网络架构的大规模计算和存储的限制。我们解决这个问题,通过压缩面部化妆转移网络与协同蒸馏和内核分解。协作蒸馏的主要思想是基于一个发现,编码器-解码器对构建一个排他性的协作关系,这被认为是一种新的知识,为低层次的视觉任务。对于核分解,我们应用卷积核的深度分离来从原始网络构建一个轻量级卷积神经网络(CNN)。大量的实验表明,压缩方法的有效性时,应用于国家的最先进的面部化妆传输网络- BeautyGAN。

英文摘要:

Although the facial makeup transfer network has achieved high-quality performance in generating perceptually pleasing makeup images, its capability is still restricted by the massive computation and storage of the network architecture. We address this issue by compressing facial makeup transfer networks with collaborative distillation and kernel decomposition. The main idea of collaborative distillation is underpinned by a finding that the encoder-decoder pairs construct an exclusive collaborative relationship, which is regarded as a new kind of knowledge for low-level vision tasks. For kernel decomposition, we apply the depth-wise separation of convolutional kernels to build a light-weighted Convolutional Neural Network (CNN) from the original network. Extensive experiments show the effectiveness of the compression method when applied to the state-of-the-art facial makeup transfer network -- BeautyGAN.

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。

↑