面向生成式人工智能的公平且鲁棒的人脸解析：一种多目标方法
Towards Fair and Robust Face Parsing for Generative AI: A Multi-Objective Approach
AI总结：
本文提出一种多目标学习框架，通过基于同伦的损失函数动态平衡准确率、公平性与鲁棒性，提升人脸解析质量，并在Pix2PixHD和ControlNet合成流程中验证其改善生成真实感与人口统计学一致性的效果。
摘要：
人脸解析是计算机视觉中的一项基础任务，支撑着身份验证、人脸编辑和可控图像合成等应用。然而，现有人脸解析模型往往缺乏公平性和鲁棒性，导致跨人口群体的分割存在偏差，并在遮挡、噪声和域偏移情况下出现错误。这些局限性会影响下游人脸合成，分割偏差可能降低生成模型的输出质量。我们提出了一种多目标学习框架，用于在人脸解析中同时优化准确率、公平性和鲁棒性。我们的方法引入了一种基于同伦的损失函数，在训练过程中动态调整这些目标的重要性。为评估其影响，我们在基于GAN的人脸合成流程（Pix2PixHD）中比较多目标与单目标U-Net模型。结果表明，公平感知且鲁棒的分割改善了人脸生成中的真实感和一致性。此外，我们使用ControlNet（一种用于基于扩散合成的结构化条件模型）进行了初步实验，以探索分割质量如何影响引导式图像生成。我们的发现表明，多目标人脸解析改善了人口统计学一致性和鲁棒性，从而带来更高质量的基于GAN的合成。
英文摘要：
Face parsing is a fundamental task in computer vision, enabling applications such as identity verification, facial editing, and controllable image synthesis. However, existing face parsing models often lack fairness and robustness, leading to biased segmentation across demographic groups and errors under occlusions, noise, and domain shifts. These limitations affect downstream face synthesis, where segmentation biases can degrade generative model outputs. We propose a multi-objective learning framework that optimizes accuracy, fairness, and robustness in face parsing. Our approach introduces a homotopy-based loss function that dynamically adjusts the importance of these objectives during training. To evaluate its impact, we compare multi-objective and single-objective U-Net models in a GAN-based face synthesis pipeline (Pix2PixHD). Our results show that fairness-aware and robust segmentation improves photorealism and consistency in face generation. Additionally, we conduct preliminary experiments using ControlNet, a structured conditioning model for diffusion-based synthesis, to explore how segmentation quality influences guided image generation. Our findings demonstrate that multi-objective face parsing improves demographic consistency and robustness, leading to higher-quality GAN-based synthesis.
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。
