Focusing on All Refined Attention Regions for Noisy Label Facial Expression Recognition

Noisy label Facial Expression Recognition (FER) poses greater challenges than traditional noisy label classification tasks, primarily due to inter-class similarity and annotation ambiguity. In this paper, we observe that FER models memorize noisy samples by emphasizing local features considered relevant to the noisy labels. Motivated by this insight, we propose a novel Focus All Network (FAN) to suppress the learning of noisy samples. Similar to human vision, our network repetitively directs attention to various parts of the image, achieving full attention to faces and focusing on subtle distinguishing elements within each expression category. A simple attention model effectively aggregates these finer details, honing in on the most influential discriminative components of the image and correcting potential attention bias. Moreover, the simplicity of our network makes it a plug-and-play module. Extensive experiments on multiple expression benchmarks demonstrate that our method achieves competitive results.