GAIA：探究基于梯度的归因异常用于分布外检测
GAIA: Delving into Gradient-based Attribution Abnormality for Out-of-distribution Detection
AI总结：
本文提出GAIA方法，通过分析梯度归因中的零收缩异常和通道平均异常来检测分布外样本，在CIFAR和ImageNet-1k上显著降低了FPR95。
摘要：
检测分布外（OOD）样本对于保证深度神经网络在真实场景中的可靠性和安全性至关重要。本文提供了一个创新的视角来量化分布内（ID）与OOD数据之间的差异——分析模型在尝试解释其预测决策时产生的不确定性。这一视角源于我们的观察：基于梯度的归因方法在为OOD数据分配特征重要性时遇到困难，从而产生发散的归因模式。据此，我们研究了归因梯度如何导致不确定的解释结果，并引入了两种用于OOD检测的异常形式：零收缩异常和通道平均异常。随后我们提出了GAIA，一种简单有效的方法，融合了梯度异常检测与聚合。GAIA的有效性在常用基准（CIFAR）和大规模基准（ImageNet-1k）上均得到验证。具体而言，与先进的事后方法相比，GAIA在CIFAR10上将平均FPR95降低了23.10%，在CIFAR100上降低了45.41%。
英文摘要：
Detecting out-of-distribution (OOD) examples is crucial to guarantee the reliability and safety of deep neural networks in real-world settings. In this paper, we offer an innovative perspective on quantifying the disparities between in-distribution (ID) and OOD data -- analyzing the uncertainty that arises when models attempt to explain their predictive decisions. This perspective is motivated by our observation that gradient-based attribution methods encounter challenges in assigning feature importance to OOD data, thereby yielding divergent explanation patterns. Consequently, we investigate how attribution gradients lead to uncertain explanation outcomes and introduce two forms of abnormalities for OOD detection: the zero-deflation abnormality and the channel-wise average abnormality. We then propose GAIA, a simple and effective approach that incorporates Gradient Abnormality Inspection and Aggregation. The effectiveness of GAIA is validated on both commonly utilized (CIFAR) and large-scale (ImageNet-1k) benchmarks. Specifically, GAIA reduces the average FPR95 by 23.10% on CIFAR10 and by 45.41% on CIFAR100 compared to advanced post-hoc methods.
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。
