Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition
It addresses annotation ambiguity for facial expression recognition, an incremental improvement in a domain-specific task.
The paper tackles annotation ambiguity in Facial Expression Recognition by proposing DMUE, which mines latent label distributions and estimates pairwise uncertainty, achieving leading performance on real-world and synthetic noisy benchmarks.
Due to the subjective annotation and the inherent interclass similarity of facial expressions, one of key challenges in Facial Expression Recognition (FER) is the annotation ambiguity. In this paper, we proposes a solution, named DMUE, to address the problem of annotation ambiguity from two perspectives: the latent Distribution Mining and the pairwise Uncertainty Estimation. For the former, an auxiliary multi-branch learning framework is introduced to better mine and describe the latent distribution in the label space. For the latter, the pairwise relationship of semantic feature between instances are fully exploited to estimate the ambiguity extent in the instance space. The proposed method is independent to the backbone architectures, and brings no extra burden for inference. The experiments are conducted on the popular real-world benchmarks and the synthetic noisy datasets. Either way, the proposed DMUE stably achieves leading performance.