用证据学习检测多标签数据中的分布外样本，提升模型鲁棒性。
Multi-label out-of-distribution detection via evidential learning
- 基于贝塔证据神经网络，同时计算预测概率与不确定性
- 在三个主流数据集上优于现有最优方法
- 适合需要可靠异常检测的视觉识别场景
机器学习模型不仅要表现良好，还需在遇到新场景时具备鲁棒性和适应性。一种实现方式是让深度模型具备分布外（OOD）数据检测能力，即识别与训练数据分布不同的样本。当这些样本为多标签时，问题更加复杂。本文提出一种基于证据深度学习的方法，用于解决视觉识别中的多标签OOD检测挑战。具体而言，设计了一种使用贝塔证据神经网络的CNN架构，可同时计算样本的似然和预测不确定性。基于此，提出了两种新的基于不确定性的OOD检测评分：(i) OOD-score Max，基于最大证据；(ii) OOD-score-Sum，综合所有输出的证据。在PASCAL-VOC、MS-COCO和NUS-WIDE三个广泛使用的数据集上进行了大量实验，结果表明该方法优于多个最先进方法。
原文摘要 · Abstract (English)
A crucial requirement for machine learning algorithms is not only to perform well, but also to show robustness and adaptability when encountering novel scenarios. One way to achieve these characteristics is to endow the deep learning models with the ability to detect out-of-distribution (OOD) data, i.e. data that belong to distributions different from the one used during their training. It is even a more complicated situation, when these data usually are multi-label. In this paper, we propose an approach based on evidential deep learning in order to meet these challenges applied to visual recognition problems. More concretely, we designed a CNN architecture that uses a Beta Evidential Neural Network to compute both the likelihood and the predictive uncertainty of the samples. Based on these results, we propose afterwards two new uncertainty-based scores for OOD data detection: (i) OOD - score Max, based on the maximum evidence; and (ii) OOD score - Sum, which considers the evidence from all outputs. Extensive experiments have been carried out to validate the proposed approach using three widely-used datasets: PASCAL-VOC, MS-COCO and NUS-WIDE, demonstrating its outperformance over several State-of-the-Art methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。