Enhancing Multi-view Open-set Learning via Ambiguity Uncertainty Calibration and View-wise Debiasing
Lists
Only you see this
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. The source code are available https://github.com/ZihanFang11/2025_MOCD_ACMMM
BibTeX
@misc{fang2025enhancing,
author = {Zihan Fang and Zhiyong Xu and Lan Du and Shide Du and Zhiling Cai and Shiping Wang},
title = {{Enhancing Multi-view Open-set Learning via Ambiguity Uncertainty Calibration and View-wise Debiasing}},
year = {2025},
eprint = {2508.01227},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2508.01227},
}