研究人员引入了一个名为共形预测自校准（CPSC）的新框架，以应对多模态学习中的挑战，特别是处理以模态不平衡和噪声腐蚀为特征的低质量数据。CPSC集成了自校准训练循环以及表示和梯度自校准模块，利用共形预测来评估实例的可靠性并指导学习过程。在六个数据集上的实验表明，CPSC在不平衡和噪声场景中均优于现有方法。 AI
影响 引入了一种提高多模态学习鲁棒性的新方法，有可能在具有不完美数据的实际应用中提高性能。
排序理由 这是一篇详细介绍多模态学习新框架的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
Multimodal learning often grapples with the challenge of low-quality data, which predominantly manifests as two facets: modality imbalance and noisy corruption. While these issues are often studied in isolation, we argue that they share a common root in the predictive uncertainty…
arXiv:2605.03820v1 Announce Type: new Abstract: Multimodal learning often grapples with the challenge of low-quality data, which predominantly manifests as two facets: modality imbalance and noisy corruption. While these issues are often studied in isolation, we argue that they s…