关于合成数据集在面部表情识别中的适用性
On Applicability of Synthetic Datasets for Facial Expression Recognition
AI总结：
本文研究了合成数据集在面部表情识别中的应用，提出三种隐私保护策略来构建平衡的数据集，并通过实验验证了合成数据在缓解类别不平衡和隐私限制方面的有效性。
摘要：
面部表情识别面临两个核心挑战。第一个是公共数据集中类别不平衡的问题，这会扭曲学习过程并削弱泛化能力。第二个是隐私和数据收集限制的问题，这限制了面部图像的共享并阻碍了大而平衡数据集的创建。为了解决这些问题，我们考察了三种互补的策略，用于在标准七种离散面部表情类别设置下构建隐私保护的面部表情识别（FER）数据集。我们的策略是：（i）在置信度阈值方案下使用教师模型对大规模未标记面部集合进行伪标签；（ii）使用扩散模型进行提示驱动的合成，条件于人口统计学属性；（iii）任务感知的基于GAN的表情编辑，该方法在保持身份和真实感的同时修改面部表情。在训练和评估中，我们采用了广泛使用的数据集，包括AffectNet、RAF-DB和FER2013。我们利用合成数据集DigiFace、DCFace和EmoNet-Face BIG作为伪标签的未标记源。此外，我们利用FFHQ数据集作为生成合成的来源。主要实验使用经典CNN主干网络IR50进行，我们还探索了更复杂的架构POSTERv1，以评估其可行性和鲁棒性。通过跨数据集评估，我们分析了每种策略在整理数据集中的权衡。研究结果展示了合成数据如何有效替代或与真实数据集结合，以缓解不平衡和隐私限制的问题。代码和生成数据集：https://www.github.com/AliAZ98/SyntFER
英文摘要：
Facial Expression Recognition faces two core challenges. The first is class imbalance in public datasets, which skews the learning process and weakens generalization. The second is related to privacy and data collection constraints, which limit the sharing of facial images and restrict the creation of large, balanced datasets. To address these issues, we examine three complementary strategies for constructing privacy-preserving FER datasets in the standard seven discrete facial expression classes setting. Our strategies are: (i) pseudo-labeling large unlabeled face collections with a teacher model under a confidence-thresholding scheme, (ii) prompt-driven synthesis using diffusion models conditioned on demographic attributes, and (iii) task-aware GAN-based expression editing that modifies facial expression while preserving identity and realism. For training and evaluation, we employed widely adopted datasets, including AffectNet, RAF-DB, and FER2013. We utilized the synthetic datasets DigiFace, DCFace, and EmoNet-Face BIG as unlabeled sources for pseudo-labeling. Additionally, we utilized the FFHQ dataset as the source for generative synthesis. The main experiments are conducted using a classic CNN backbone, IR50, and we also explore a more complex architecture, POSTERv1, to assess its feasibility and robustness. Using cross-dataset evaluations, we analyze the trade-offs each strategy presents in curated datasets. The findings demonstrate how synthetic data can effectively substitute or be combined with real datasets to mitigate imbalance and privacy limitations. Code and generated datasets:https://www.github.com/AliAZ98/SyntFER
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。
