Partial Multiview Incomplete Multilabel Learning Via Uncertainty-Driven Reliable Dynamic Fusion.

Currently, an increasing number of researchers are focusing on partial multiview incomplete multilabel learning. However, many methods generally integrate features from multiple views via an average weighting strategy, which overlooks the potential mismatch between the contribution of each view and their assigned fusion weights and thus generates unreliable fused features. To address this issue, we propose a novel uncertainty-driven reliable dynamic fusion framework for partial multiview incomplete multilabel learning. Unlike existing methods, the proposed uncertainty-driven reliable sample-level dynamic fusion module operates on the principle that samples exhibiting greater uncertainty possess fewer reliable features. This module evaluates the uncertainty of each sample and, in turn, estimates the reliability of features with the uncertainty of sample judgement, thereby obtaining reliable weights to guide the information fusion of multiple views. Furthermore, many existing approaches for handling incomplete multilabel scenarios typically concentrate on the information from annotated labels, neglecting the potential information of unknown tags. To bridge this gap, we incorporate an innovative pseudolabelling strategy that effectively identifies trustworthy pseudolabels that correspond to those unannotated uncertain labels, thereby adding additional supervisory information to assist model training. Moreover, we also devise a feature masking strategy to further augment the encoder's representation learning capabilities. The experimental results across five datasets demonstrate that our method outperforms current state-of-the-art methods.