LA-Net：面向标签噪声下可靠面部表情识别的关键点感知学习
LA-Net: Landmark-Aware Learning for Reliable Facial Expression Recognition under Label Noise
AI总结：
针对 FER 中噪声标签损害性能的问题，提出 LA-Net，利用面部关键点进行标签分布构建和表情-关键点对比学习，在不增加推理成本的情况下达到最先进性能。
摘要：
由于表情具有模糊性，面部表情识别（FER）仍是一项具有挑战性的任务。由此产生的噪声标签会显著损害真实场景中的性能。为解决这一问题，我们提出了一个名为 Landmark-Aware Net（LA-Net）的新型 FER 模型，该模型利用面部关键点从两个角度缓解标签噪声的影响。首先，LA-Net 使用关键点信息抑制表情空间中的不确定性，并通过邻域聚合构建每个样本的标签分布，从而提升训练监督的质量。其次，该模型利用所设计的表情-关键点对比损失，将关键点信息融入表情表示中。增强后的表情特征提取器能够更不易受到标签噪声的影响。我们的方法可以与任何深度神经网络集成，以获得更好的训练监督，且不会引入额外的推理成本。我们在野外数据集和合成噪声数据集上进行了大量实验，结果表明 LA-Net 取得了最先进的性能。
英文摘要：
Facial expression recognition (FER) remains a challenging task due to the ambiguity of expressions. The derived noisy labels significantly harm the performance in real-world scenarios. To address this issue, we present a new FER model named Landmark-Aware Net~(LA-Net), which leverages facial landmarks to mitigate the impact of label noise from two perspectives. Firstly, LA-Net uses landmark information to suppress the uncertainty in expression space and constructs the label distribution of each sample by neighborhood aggregation, which in turn improves the quality of training supervision. Secondly, the model incorporates landmark information into expression representations using the devised expression-landmark contrastive loss. The enhanced expression feature extractor can be less susceptible to label noise. Our method can be integrated with any deep neural network for better training supervision without introducing extra inference costs. We conduct extensive experiments on both in-the-wild datasets and synthetic noisy datasets and demonstrate that LA-Net achieves state-of-the-art performance.
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。
