Deep Fuzzy Multi-view Learning for Reliable Classification

Multi-view learning methods primarily focus on enhancing decision accuracy but often neglect the uncertainty arising from the intrinsic drawbacks of data, such as noise, conflicts, etc. To address this issue, several trusted multi-view learning approaches based on the Evidential Theory have been proposed to capture uncertainty in multi-view data. However, their performance is highly sensitive to conflicting views, and their uncertainty estimates, which depend on the total evidence and the number of categories, often underestimate uncertainty for conflicting multi-view instances due to the neglect of inherent conflicts between belief masses. To accurately classify conflicting multi-view instances and precisely estimate their intrinsic uncertainty, we present a novel Deep \underline{Fu}zzy \underline{M}ulti-View \underline{L}earning (\textbf{FUML}) method. Specifically, FUML leverages Fuzzy Set Theory to model the outputs of a classification neural network as fuzzy memberships, incorporating both possibility and necessity measures to quantify category credibility. A tailored loss function is then proposed to optimize the category credibility. To further enhance uncertainty estimation, we propose an entropy-based uncertainty estimation method leveraging category credibility. Additionally, we develop a Dual Reliable Multi-view Fusion (DRF) strategy that accounts for both view-specific uncertainty and inter-view conflict to mitigate the influence of conflicting views in multi-view fusion. Extensive experiments demonstrate that our FUML achieves state-of-the-art performance in terms of both accuracy and reliability.

Environmental factors, such as sensor failure, adverse weather conditions, and data communication issues, often introduce noisy and unaligned views in multi-view data, i.e., create conflicting views. How to correctly classify such conflicting multi-view instances and accurately estimate the corresponding uncertainty is a very realistic and critical issue. To address this challenge, we propose the powerful Deep Fuzzy Multi-view Learning method (FUML), which is based on the Fuzzy Set Theory. Our FUML can achieve trusted and reliable multi-view classification, thereby contributing to safety-critical fields such as video surveillance, medical detection, and autonomous driving.