Uncertainty Quantification via H\"older Divergence for Multi-View Representation Learning

TL;DR

This paper introduces a novel uncertainty quantification method using H"older Divergence for multi-view learning, improving reliability and robustness in noisy or incomplete data scenarios.

Contribution

The paper proposes a new algorithm based on H"older Divergence for better uncertainty estimation in multi-view learning, addressing limitations of KL divergence and enhancing performance.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Demonstrates high robustness with noisy and incomplete data.

Improves multi-class recognition accuracy.

Abstract

Evidence-based deep learning represents a burgeoning paradigm for uncertainty estimation, offering reliable predictions with negligible extra computational overheads. Existing methods usually adopt Kullback-Leibler divergence to estimate the uncertainty of network predictions, ignoring domain gaps among various modalities. To tackle this issue, this paper introduces a novel algorithm based on H\"older Divergence (HD) to enhance the reliability of multi-view learning by addressing inherent uncertainty challenges from incomplete or noisy data. Generally, our method extracts the representations of multiple modalities through parallel network branches, and then employs HD to estimate the prediction uncertainties. Through the Dempster-Shafer theory, integration of uncertainty from different modalities, thereby generating a comprehensive result that considers all available representations. Mathematically, HD proves to better measure the ``distance'' between real data distribution and predictive distribution of the model and improve the performances of multi-class recognition tasks. Specifically, our method surpass the existing state-of-the-art counterparts on all evaluating benchmarks. We further conduct extensive experiments on different backbones to verify our superior robustness. It is demonstrated that our method successfully pushes the corresponding performance boundaries. Finally, we perform experiments on more challenging scenarios, \textit{i.e.}, learning with incomplete or noisy data, revealing that our method exhibits a high tolerance to such corrupted data.