通过自适应融合多个最高置信度值，提升模型对异常数据的检测能力。
Out-of-Distribution Detection with Adaptive Top-K Logits Integration
- 自适应选取关键置信度值进行融合，比单一最大置信度更有效。
- 在ImageNet-1K上将误报率降低6.73%（相比MaxLogit）。
- 适合关注模型安全性的研究人员，尤其在部署场景中使用。
神经网络对分布外（OOD）样本常做出过度自信的预测，因此检测OOD数据对提升机器学习安全性至关重要。目前最简单且有效的检测方法是MaxLogit，它利用模型最大置信度作为OOD评分。我们发现，除最大置信度外，其他若干高置信度值也对检测有帮助。基于此，提出ATLI（自适应顶k置信度融合）方法：根据每个模型特性自适应选择有效顶k置信度，并与最大置信度融合。在ImageNet-1K基准上的实验表明，该方法相较MaxLogit将FPR95降低6.73%，比其他先进方法再降2.67%。
原文摘要 · Abstract (English)
Neural networks often make overconfident predictions from out-of-distribution (OOD) samples. Detection of OOD data is therefore crucial to improve the safety of machine learning. The simplest and most powerful method for OOD detection is MaxLogit, which uses the model's maximum logit to provide an OOD score. We have discovered that, in addition to the maximum logit, some other logits are also useful for OOD detection. Based on this finding, we propose a new method called ATLI (Adaptive Top-k Logits Integration), which adaptively determines effective top-k logits that are specific to each model and combines the maximum logit with the other top-k logits. In this study we evaluate our proposed method using ImageNet-1K benchmark. Extensive experiments showed our proposed method to reduce the false positive rate (FPR95) by 6.73% compared to the MaxLogit approach, and decreased FPR95 by an additional 2.67% compared to other 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。