We introduce Foveation-based Explanations (FovEx), a novel human-inspired visual explainability (XAI) method for Deep Neural Networks. Our method achieves state-of-the-art performance on both transformer (on 4 out of 5 metrics) and convolutional models (on 3 out of 5 metrics), demonstrating its versatility. Furthermore, we show the alignment between the explanation map produced by FovEx and human gaze patterns (+14\% in NSS compared to RISE, +203\% in NSS compared to gradCAM), enhancing our confidence in FovEx's ability to close the interpretation gap between humans and machines.

翻译：本文提出Foveation-based Explanations (FovEx)，一种受人类视觉启发的深度神经网络视觉可解释性新方法。该方法在Transformer模型（5项指标中4项领先）与卷积模型（5项指标中3项领先）上均达到最先进的性能表现，展现了其广泛的适用性。此外，我们证明FovEx生成的解释图与人类注视模式具有高度一致性（在NSS指标上较RISE提升14%，较gradCAM提升203%），这增强了我们对FovEx能够弥合人机解释鸿沟的信心。