Data augmentation has been proven effective for training high-accuracy convolu-tional neural network classifiers by preventing overfitting.

These methodologies typically lead to performance bottlenecks and unsatisfactory generalizability.

However, such a global learning rate schedule does not take into account the structural characteristics of neural networks (NNs).

Our motivation is grounded in a fundamental observation: aligning the gradient and the Hessian of the SDF provides a more efficient mechanism to govern gradient directions.