GAIA: Delving into Gradient-based Attribution Abnormality for Out-of-distribution Detection
Motivation of our workAbstract
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 significantly 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. Our approach can be readily applied to pre-trained models without the need for further fine-tuning or additional training. Experimental results demonstrate that GAIA surpasses state-of-the-art methods on both commonly utilized (CIFAR) and large-scale (ImageNet) benchmarks. Specifically, GAlA exhibits superior performance on CIFAR benchmarks, reducing the average FPR95 by 26.75% on CIFAR10 and by 45.41% on CIFAR100 compared to competing approaches.
