Enhancing Multi-view Open-set Learning via Ambiguity Uncertainty Calibration and View-wise Debiasing

TL;DR

This paper introduces a novel multi-view open-set learning framework that uses ambiguity uncertainty calibration and view-wise debiasing to improve recognition of unknown classes and reduce view-induced biases.

Contribution

It proposes O-Mix for synthesizing ambiguous samples and an HSIC-based contrastive debiasing module to enhance open-set recognition in multi-view learning.

Findings

Improves unknown-class recognition accuracy.

Maintains strong closed-set performance.

Effective across diverse benchmarks.

Abstract

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.