Semi-Supervised Texture Filtering With Shallow to Deep Understanding
Semi-Supervised Texture Filtering With Shallow to Deep Understanding
复制标题
从浅到深理解的半监督纹理过滤
DOI：
10.1109/tip.2020.3004043
复制
发表时间：
2020-01-01
影响因子：
10.6
通讯作者：
Wang, Wencheng
中科院分区：
文献类型：
--
作者：
Gao, Xing;Wu, Xu;Wang, Wencheng
提出了一种半监督的纹理自动滤波方法。我们的方法利用了有限数量的标记数据和大量的未标记数据来训练生成对抗网络（GAN）。为标记和未标记数据集设计了单独的损失函数。我们的主要贡献是介绍了从神经网络的浅层和深层提取的知识。在浅层内定义的损失保留边缘，而在深层内定义的损失识别语义内容，并相反地移除小尺度纹理变化。这一贡献直接解决了纹理过滤的主要挑战，在像素级区分结构性内容和非结构性纹理。提取的信息，在我们的研究中，提高了过滤过程前后的内容和颜色的一致性，特别是对于未标记的样本。所提出的方法提供了两个好处：第一，显着减少了重建标记数据集所花费的时间和精力，特别是考虑到像素级所需的精细操作;第二，通过利用大量的未标记数据，在少量标记数据的监督学习中，减少了过度拟合。结果证实，我们的方法可以执行与非基于学习的方法，减轻了最佳参数值的确定的需求。
This work proposed a semi-supervised method for automatic texture filtering. Our method leveraged a limited amount of labeled data and a large amount of unlabeled data to train Generative Adversarial Networks (GANs). Separate loss functions were designed for both labeled and unlabeled datasets. Our main contribution is the introduction of knowledge extracted from shallow and deep layers in neural networks. Loss defined within shallow layers preserves the edge, while loss defined within the deep layers identifies the semantic content and conversely removes the small-scale texture variations. This contribution directly addresses the major challenge for texture filtering, distinguishing the structural content from non-structural textures at the pixel level. The extracted information, in our study, improved the content and color consistency before and after the process of filtering, for unlabeled samples in particular. The proposed method offers twofold benefits: first, significant reductions in the amounts of time and effort expended in reconstructing the labeled dataset, especially given the delicate operations required at the pixel level; second, a reduction in over-fitting, in supervised learning with a small amount of labeled data, by utilizing a large amount of unlabeled data. The results confirm that our method can perform comparably with non-learning-based methods, alleviating the demand for the determination of optimal parameter values.