Although AI systems have been applied in various fields and achieved impressive performance, their safety and reliability are still a big concern. This is especially important for safety-critical tasks. One shared characteristic of these critical tasks is their risk sensitivity, where small mistakes can cause big consequences and even endanger life. There are several factors that could be guidelines for the successful deployment of AI systems in sensitive tasks: (i) failure detection and out-of-distribution (OOD) detection; (ii) overfitting identification; (iii) uncertainty quantification for predictions; (iv) robustness to data perturbations. These factors are also challenges of current AI systems, which are major blocks for building safe and reliable AI. Specifically, the current AI algorithms are unable to identify common causes for failure detection. Furthermore, additional techniques are required to quantify the quality of predictions. All these contribute to inaccurate uncertainty quantification, which lowers trust in predictions. Hence obtaining accurate model uncertainty quantification and its further improvement are challenging. To address these issues, many techniques have been proposed, such as regularization methods and learning strategies. As vision and language are the most typical data type and have many open source benchmark datasets, this thesis will focus on vision-language data processing for tasks like classification, image captioning, and vision question answering. In this thesis, we aim to build a safeguard by further developing current techniques to ensure the accurate model uncertainty for safety-critical tasks.

翻译：尽管人工智能系统已在多个领域得到应用并取得了显著性能，其安全性和可靠性仍是重大隐忧。对于安全关键型任务而言，这一问题尤为突出。此类关键任务的共同特征在于对风险的高度敏感性，微小的失误可能引发严重后果甚至危及生命。敏感任务中成功部署人工智能系统需遵循若干指导原则：(i) 故障检测与分布外（OOD）检测；(ii) 过拟合识别；(iii) 预测结果的不确定性量化；(iv) 对数据扰动的鲁棒性。这些要素当前人工智能系统面临的挑战，亦成为构建安全可靠AI的主要障碍。具体而言，现有AI算法无法识别故障检测的常见成因。此外，需要额外技术量化预测质量。这些因素共同导致不精准的不确定性量化，削弱了对预测结果的信任。因此，获取准确的模型不确定性量化及其进一步优化极具挑战性。为应对这些问题，学界已提出正则化方法、学习策略等多种技术。鉴于视觉与语言是最典型的数据类型且拥有大量开源基准数据集，本论文将聚焦于分类、图像描述及视觉问答等任务的视觉-语言数据处理。本研究旨在通过改进现有技术构建安全防护机制，确保面向安全关键任务的模型不确定性量化精度。