{"ID":2887530,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.01227","arxiv_id":"2508.01227","title":"Enhancing Multi-view Open-set Learning via Ambiguity Uncertainty Calibration and View-wise Debiasing","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.","short_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 prop...","url_abs":"https://arxiv.org/abs/2508.01227","url_pdf":"https://arxiv.org/pdf/2508.01227v2","authors":"[\"Zihan Fang\",\"Zhiyong Xu\",\"Lan Du\",\"Shide Du\",\"Zhiling Cai\",\"Shiping Wang\"]","published":"2025-08-02T06:46:16Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[]","has_code":false}