Domain-knowledge Inspired Pseudo Supervision (DIPS) for unsupervised image-to-image translation models to support cross-domain classification
Domain-knowledge Inspired Pseudo Supervision (DIPS) for unsupervised image-to-image translation models to support cross-domain classification
复制标题
DOI：
10.1016/j.engappai.2023.107255
复制
发表时间：
2023-10-11
影响因子：
8
通讯作者：
Sun, Ying
中科院分区：
文献类型：
--
作者：
Al-Hindawi, Firas;Siddiquee, Md Mahfuzur Rahman;Sun, Ying
图像分类的能力取决于能否访问大型标记数据集以及对来自模型训练的同一域的数据进行测试。当处理来自不同领域的新数据时，分类变得更具挑战性，其中收集并特别标记更大的图像数据集以重新训练分类模型需要劳动密集型的人力。跨域分类框架的开发是为了通过利用无监督的图像到图像转换模型将输入图像从未标记域转换到标记域来处理这种数据域转移问题。这些无监督模型的问题在于它们的无监督性质。由于缺乏注释，不可能使用传统的监督指标来评估这些翻译模型以选择保存最好的检查点模型。本文介绍了一种称为领域知识启发伪监督（DIPS）的新方法，该方法利用高斯混合模型和领域知识生成伪注释，以实现传统监督指标的使用。该方法专门为支持跨域分类应用而设计，与其他常用指标（例如 Frechet 起始距离 (FID)）相反，FID 旨在从人眼角度评估生成图像的质量。在选择最佳保存检查点时，DIPS 的性能优于最先进的 GAN 评估指标。此外，DIPS 通过展示与真正监督指标的强相关性来展示其稳健性和可解释性，强调其相对于现有最先进替代方案的优越性。沸腾危机问题已作为案例研究。复制结果的代码和数据可以在官方 GitHub-repository1 上找到。
The ability to classify images is dependent on having access to large labeled datasets and testing on data from the same domain of which the model was trained on. Classification becomes more challenging when dealing with new data from a different domain, where gathering and especially labeling a larger image dataset for retraining a classification model requires a labor-intensive human effort. Cross-domain classification frameworks were developed to handle this data domain shift problem by utilizing unsupervised image-to-image translation models to translate an input image from the unlabeled domain to the labeled domain. The problem with these unsupervised models lies in their unsupervised nature. For lack of annotations, it is not possible to use the traditional supervised metrics to evaluate these translation models to pick the best-saved checkpoint model. This paper introduces a new method called Domain-knowledge Inspired Pseudo Supervision (DIPS) which utilizes Gaussian Mixture Models and domain knowledge to generate pseudo annotations to enable the use of traditional supervised metrics. This method was designed specifically to support cross-domain classification applications contrary to other typically used metrics such as the Frechet Inception Distance (FID) which were designed to evaluate the model in terms of the quality of the generated image from a human-eye perspective. DIPS outperforms state-of-the-art GAN evaluation metrics when selecting the optimal saved checkpoint. Furthermore, DIPS showcases its robustness and interpretability by demonstrating a strong correlation with truly supervised metrics, highlighting its superiority over existing state-of-the-art alternatives The boiling crisis problem has been approached as a case study. The code and data to replicate the results can be found on the official GitHub-repository1.