Recent advancements in learning algorithms have demonstrated that the sharpness of the loss surface is an effective measure for improving the generalization gap. Building upon this concept, Sharpness-Aware Minimization (SAM) was proposed to enhance model generalization and achieved state-of-the-art performance. SAM consists of two main steps, the weight perturbation step and the weight updating step. However, the perturbation in SAM is determined by only the gradient of the training loss, or cross-entropy loss. As the model approaches a stationary point, this gradient becomes small and oscillates, leading to inconsistent perturbation directions and also has a chance of diminishing the gradient. Our research introduces an innovative approach to further enhancing model generalization. We propose the Adaptive Adversarial Cross-Entropy (AACE) loss function to replace standard cross-entropy loss for SAM's perturbation. AACE loss and its gradient uniquely increase as the model nears convergence, ensuring consistent perturbation direction and addressing the gradient diminishing issue. Additionally, a novel perturbation-generating function utilizing AACE loss without normalization is proposed, enhancing the model's exploratory capabilities in near-optimum stages. Empirical testing confirms the effectiveness of AACE, with experiments demonstrating improved performance in image classification tasks using Wide ResNet and PyramidNet across various datasets. The reproduction code is available online

近期学习算法的进展表明，损失曲面的陡峭程度是提高泛化差距的有效指标。本研究引入创新的方法进一步增强模型泛化能力，提出了自适应对抗交叉熵（AACE）损失函数替代Sharpness-Aware Minimization（SAM）的扰动，同时提出了一种利用AACE损失生成扰动的新方法，实验证实了AACE的有效性，并通过在各种数据集上使用Wide ResNet和PyramidNet进行图像分类任务的实验，取得了改进的性能。

自适应对抗性交叉熵损失用于尖锐感知最小化