可控面部操纵与合成用于数据增强
Controlled Face Manipulation and Synthesis for Data Augmentation
AI总结：
本文提出了一种在语义潜在空间中进行可控面部操纵的方法，通过减少语义特征交织和去除噪声属性，提升AU检测器的准确性和解耦预测能力。
摘要：
深度学习视觉模型在充足监督下表现优异，但许多应用面临标签稀缺和类别不平衡的问题。可控图像编辑可以增强稀缺的标记数据，但编辑常常引入伪影并使非目标属性交织。我们研究了面部表情分析中的这一问题，针对动作单元（AU）操纵，其中标注成本高且AU共激活驱动交织。我们提出了一种面部操纵方法，该方法在预训练的面部生成器（扩散自编码器）的语义潜在空间中运行。使用轻量级线性模型，我们通过（i）依赖感知的条件化，考虑AU共激活，以及（ii）正交投影，去除噪声属性方向（例如眼镜），再加上一个表达中性化步骤，以实现绝对AU编辑。我们利用这些编辑来平衡AU出现频率，通过编辑标记面孔，并通过受控合成来多样化身份和人口统计数据。通过将生成的数据用于AU检测器训练，提高了准确性，并产生了更具解耦的预测，且共激活捷径更少，优于替代的数据高效训练策略，并在我们的学习曲线分析中表明，与需要大量标记数据的改进相似。与先前方法相比，我们的编辑更强，产生的伪影更少，并且更好地保留了身份。
英文摘要：
Deep learning vision models excel with abundant supervision, but many applications face label scarcity and class imbalance. Controllable image editing can augment scarce labeled data, yet edits often introduce artifacts and entangle non-target attributes. We study this in facial expression analysis, targeting Action Unit (AU) manipulation where annotation is costly and AU co-activation drives entanglement. We present a facial manipulation method that operates in the semantic latent space of a pre-trained face generator (Diffusion Autoencoder). Using lightweight linear models, we reduce entanglement of semantic features via (i) dependency-aware conditioning that accounts for AU co-activation, and (ii) orthogonal projection that removes nuisance attribute directions (e.g., glasses), together with an expression neutralization step to enable absolute AU edit. We use these edits to balance AU occurrence by editing labeled faces and to diversify identities/demographics via controlled synthesis. Augmenting AU detector training with the generated data improves accuracy and yields more disentangled predictions with fewer co-activation shortcuts, outperforming alternative data-efficient training strategies and suggesting improvements similar to what would require substantially more labeled data in our learning-curve analysis. Compared to prior methods, our edits are stronger, produce fewer artifacts, and preserve identity better.
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。
