Pseudo-Multiview Learning Using Subjective Logic for Enhanced Classification Accuracy

Deep learning has significantly advanced image classification by leveraging hierarchical feature representations. A key factor in enhancing classification accuracy is feature concatenation, which integrates diverse feature sets to provide a richer representation of input data. However, this fusion strategy has inherent limitations, including increased computational complexity, susceptibility to redundant or irrelevant features, and challenges in optimally weighting different feature contributions. To address these challenges, this paper presents a pseudo-multiview learning method that dynamically combines different views at the evidence level using a belief-based model known as subjective logic. This approach adaptively assigns confidence levels to each view, ensuring more effective integration of complementary information while mitigating the impact of noisy or less relevant features. Experimental evaluations of datasets from various domains demonstrate that the proposed method enhances classification accuracy and robustness compared with conventional classification techniques.