Abstract
The goal of this paper is to enhance face recognition performance by augmenting head poses during the testing phase. Existing methods often rely on training on frontalised images or learning pose-invariant representations, yet both approaches typically require re-training and testing for each dataset, involving a substantial amount of effort. In contrast, this study proposes Pose-TTA, a novel approach that aligns faces at inference time without additional training. To achieve this, we employ a portrait animator that transfers the source image identity into the pose of a driving image. Instead of frontalising a side-profile face -- which can introduce distortion -- Pose-TTA generates matching side-profile images for comparison, thereby reducing identity information loss. Furthermore, we propose a weighted feature aggregation strategy to address any distortions or biases arising from the synthetic data, thus enhancing the reliability of the augmented images. Extensive experiments on diverse datasets and with various pre-trained face recognition models demonstrate that Pose-TTA consistently improves inference performance. Moreover, our method is straightforward to integrate into existing face recognition pipelines, as it requires no retraining or fine-tuning of the underlying recognition models.
Abstract (translated)
本文的目标是通过在测试阶段增强头部姿态来提高面部识别的性能。现有的方法通常依赖于使用正面化的图像进行训练或学习位置不变表示，然而这两种方法通常都需要为每个数据集重新进行训练和测试，涉及大量的工作量。相比之下，本研究提出了一种名为Pose-TTA的新方法，在推理时对齐面部而无需额外训练。 为了实现这一目标，我们采用了肖像动画师来将源图像的身份转移到驱动图像的姿态中。与正面化侧面轮廓脸不同（这可能会引入失真），Pose-TTA生成用于比较的匹配侧面轮廓图像，从而减少身份信息损失。 此外，我们提出了一种加权特征聚合策略，以解决由合成数据引起的任何失真或偏差问题，从而使增强图像更加可靠。 在各种数据集和不同的预训练面部识别模型上进行的大量实验表明，Pose-TTA可以一致地提高推理性能。而且，我们的方法易于集成到现有的面部识别管道中，因为它不需要对底层识别模型进行重新训练或微调。
URL
https://arxiv.org/abs/2505.09256
