Enhancing Multi-view Open-set Learning via Ambiguity Uncertainty Calibration and View-wise Debiasing
This work addresses the challenge of recognizing unknown categories in multi-view learning, which is important for applications like computer vision and data fusion, but it appears incremental as it builds on existing multi-view and open-set learning methods.
The paper tackles the problem of multi-view learning in open-set scenarios, where existing models fail due to class completeness assumptions and view-induced biases, by proposing a framework with ambiguity uncertainty calibration and view-wise debiasing, resulting in enhanced unknown-class recognition and strong closed-set performance across diverse benchmarks.
Existing multi-view learning models struggle in open-set scenarios due to their implicit assumption of class completeness. Moreover, static view-induced biases, which arise from spurious view-label associations formed during training, further degrade their ability to recognize unknown categories. In this paper, we propose a multi-view open-set learning framework via ambiguity uncertainty calibration and view-wise debiasing. To simulate ambiguous samples, we design O-Mix, a novel synthesis strategy to generate virtual samples with calibrated open-set ambiguity uncertainty. These samples are further processed by an auxiliary ambiguity perception network that captures atypical patterns for improved open-set adaptation. Furthermore, we incorporate an HSIC-based contrastive debiasing module that enforces independence between view-specific ambiguous and view-consistent representations, encouraging the model to learn generalizable features. Extensive experiments on diverse multi-view benchmarks demonstrate that the proposed framework consistently enhances unknown-class recognition while preserving strong closed-set performance.