Answers are grounded in this paper and cite their sources.
Semi-Supervised Deep Facial Expression Recognition (SS-DFER) has gained significant attention due to its utilization of large amounts of unlabeled data. However, SS-DFER faces two main problems, ambiguity in facial semantics caused by noisy labels and poor feature representation capabilities of models. In this paper, we propose a novel SS-DFER method based on Semantic-level and Instance-Level information Interactive Mining, namely SILIM, to simultaneously address both problems. Specifically, the model generates pseudo-labels for semantics and instances through the interaction of semantic and instance information, achieving matching at both levels to fully exploit image feature information. In addition, we construct a memory buffer that stores all instances of labeled data, enabling interaction between semantic pseudo-labels and instance pseudo-labels. For this, we design a neighbor-node-based instance space optimization strategy. This prevents degradation in module’s feature representation ability caused by pushing away instances of the same image category, thereby optimizing decision boundaries. Experiments on four challenging facial expression datasets show that our method significantly outperforms the second-best state-of-the-art SS-DFER method and surpasses the fully-supervised baselines.
No takes yet. Share an insight, caveat, or question.
Jiliu Zhou (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: