Generated Image Editing Method Based on Global-Local Jacobi Disentanglement for Machine Learning.
Generated Image Editing Method Based on Global-Local Jacobi Disentanglement for Machine Learning.
复制标题
DOI：
10.3390/s23041815
复制
发表时间：
2023-02-06
期刊：
影响因子：
--
通讯作者：
Chen C
中科院分区：
文献类型：
--
作者：
Zhang J;Yu X;Wang B;Chen C
对生成的图像进行准确的语义编辑对于机器学习和大数据的样本增强至关重要。针对StyleGAN2网络生成图像潜在空间中的语义纠缠问题，提出了一种基于全局-局部Jacobi解缠的生成图像编辑方法。在全局解缠方面，提取预训练的StyleGAN2网络中样式层的权值矩阵；利用权值矩阵特征分解方法得到语义属性方向向量；最后，将该方向向量作为Jacobi正则化搜索算法的初始化向量。该方法利用有效语义属性编辑方向的比例，提高了Jacobi正则化搜索算法的速度。在局部解缠方面，设计了局部对比度正则化损失函数来松弛语义关联的局部区域和非局部区域，并利用Jacobi正交正则化搜索算法在局部区域先验掩码的基础上得到更准确的语义属性编辑方向。实验结果表明，与主流的非监督生成图像编辑方法相比，该方法在语义属性解缠度量上实现了SOTA，并能发现更准确的编辑方向。
Accurate semantic editing of the generated images is extremely important for machine learning and sample enhancement of big data. Aiming at the problem of semantic entanglement in generated image latent space of the StyleGAN2 network, we proposed a generated image editing method based on global-local Jacobi disentanglement. In terms of global disentanglement, we extract the weight matrix of the style layer in the pre-trained StyleGAN2 network; obtain the semantic attribute direction vector by using the weight matrix eigen decomposition method; finally, utilize this direction vector as the initialization vector for the Jacobi orthogonal regularization search algorithm. Our method improves the speed of the Jacobi orthogonal regularization search algorithm with the proportion of effective semantic attribute editing directions. In terms of local disentanglement, we design a local contrast regularized loss function to relax the semantic association local area and non-local area and utilize the Jacobi orthogonal regularization search algorithm to obtain a more accurate semantic attribute editing direction based on the local area prior MASK. The experimental results show that the proposed method achieves SOTA in semantic attribute disentangled metrics and can discover more accurate editing directions compared with the mainstream unsupervised generated image editing methods.
登录
查看更多内容
影响因子：
3.2
作者：
Abdi, Herve;Williams, Lynne J.
通讯作者：
Williams, Lynne J.
影响因子：
6.4
作者：
Chen, Chen;Jiang, Jiange;Pei, Qingqi
通讯作者：
Pei, Qingqi
影响因子：
10.6
作者：
Chen, Chen;Zeng, Yini;Wan, Shaohua
通讯作者：
Wan, Shaohua
影响因子：
5
作者：
Chen, Chen;Fu, Rufei;Pei, Qingqi
通讯作者：
Pei, Qingqi
影响因子：
10.6
作者：
Liu, Kanglin;Cao, Gaofeng;Qiu, Guoping
通讯作者：
Qiu, Guoping