文本异常值暴露在视觉 OoD 检测中的强大能力
On the Powerfulness of Textual Outlier Exposure for Visual OoD Detection
AI总结：
本文首次探索文本异常值暴露用于视觉 OoD 检测，提出多种生成文本异常值的方法，并在大规模基准上取得竞争力，总结出近分布、描述性和视觉语义三大设计标准。
摘要：
成功检测分布外（OoD）数据对于确保神经网络的安全部署正变得越来越重要。OoD 检测的主要挑战之一是神经网络在 OoD 数据上输出过度自信的预测，这使得仅基于预测结果来确定数据的 OoD 特性变得困难。异常值暴露通过引入额外的损失来解决这一问题，该损失在训练期间鼓励对 OoD 数据做出低置信度预测。尽管异常值暴露在提升 OoD 检测性能方面展现出可喜的潜力，但以往所有关于异常值暴露的研究都局限于利用视觉异常值。受视觉-语言预训练最新进展的启发，本文涉足了文本异常值暴露这一未知领域。首先，我们通过用文本等价物替换图像域中的真实或虚拟异常值，揭示了使用文本异常值的益处。然后，我们提出了多种生成理想文本异常值的方法。我们的大量实验表明，生成的文本异常值在大规模 OoD 和困难 OoD 基准上取得了具有竞争力的性能。此外，我们对文本异常值进行了实证分析，为设计有利的文本异常值提供了主要标准：近分布、描述性和包含视觉语义。
英文摘要：
Successful detection of Out-of-Distribution (OoD) data is becoming increasingly important to ensure safe deployment of neural networks. One of the main challenges in OoD detection is that neural networks output overconfident predictions on OoD data, make it difficult to determine OoD-ness of data solely based on their predictions. Outlier exposure addresses this issue by introducing an additional loss that encourages low-confidence predictions on OoD data during training. While outlier exposure has shown promising potential in improving OoD detection performance, all previous studies on outlier exposure have been limited to utilizing visual outliers. Drawing inspiration from the recent advancements in vision-language pre-training, this paper venture out to the uncharted territory of textual outlier exposure. First, we uncover the benefits of using textual outliers by replacing real or virtual outliers in the image-domain with textual equivalents. Then, we propose various ways of generating preferable textual outliers. Our extensive experiments demonstrate that generated textual outliers achieve competitive performance on large-scale OoD and hard OoD benchmarks. Furthermore, we conduct empirical analyses of textual outliers to provide primary criteria for designing advantageous textual outliers: near-distribution, descriptiveness, and inclusion of visual semantics.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
