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

arXiv: https://arxiv.org/abs/2508.01227 · HTML: https://mlsanity.com/paper/2508.01227/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 34 references that are in the map.
- First posted on arXiv 2 Aug 2025.

## Builds on (most cited first, 13 of 13)

- [Reducing Network Agnostophobia](https://mlsanity.com/paper/1811.04110/) (2018)
- [Evidential Deep Learning for Open Set Action Recognition](https://mlsanity.com/paper/2107.10161/) (2021)
- [Trusted Multi-View Classification](https://mlsanity.com/paper/2102.02051/) (2021)
- [Reliable Conflictive Multi-View Learning](https://mlsanity.com/paper/2402.16897/) (2024)
- [OpenMix: Exploring Outlier Samples for Misclassification Detection](https://mlsanity.com/paper/2303.17093/) (2023)
- [UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup](https://mlsanity.com/paper/2209.08928/) (2022)
- [Deep Incomplete Multi-view Clustering with Cross-view Partial Sample and Prototype Alignment](https://mlsanity.com/paper/2303.15689/) (2023)
- [Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification](https://mlsanity.com/paper/2409.00755/) (2024)
- [Generalized Evidence Theory](https://mlsanity.com/paper/1404.4801/) (2014)
- [FUGNN: Harmonizing Fairness and Utility in Graph Neural Networks](https://mlsanity.com/paper/2405.17034/) (2024)
- [Adaptively-weighted Integral Space for Fast Multiview Clustering](https://mlsanity.com/paper/2208.12808/) (2022)
- [Scalable Incomplete Multi-View Clustering with Structure Alignment](https://mlsanity.com/paper/2308.16541/) (2023)
- [Disentangling Multi-view Representations Beyond Inductive Bias](https://mlsanity.com/paper/2308.01634/) (2023)

## Built on by (most cited first, 1 of 1)

- [Are Independently Estimated View Uncertainties Comparable? Unified Routing for Trusted Multi-View Classification](https://mlsanity.com/paper/2604.09288/) (2026)

## Abstract (arXiv)

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.