论文标题
值得信赖的卷积神经网络：一种基于梯度惩罚的方法
Trustworthy Convolutional Neural Networks: A Gradient Penalized-based Approach
论文作者
论文摘要
卷积神经网络（CNN）通常用于图像分类。显着性方法是可用于解释CNN事后CNN的方法的示例，可以在梯度流下识别预测的最相关像素。即使CNN可以正确地对图像进行分类，但在许多情况下，潜在的显着图可能是错误的。这可能会导致对模型的有效性或其解释的持怀疑态度。我们提出了一种新颖的方法来训练可信赖的CNN，通过惩罚参数选择，从而导致训练过程中产生的显着性图不准确。我们为预测标签正确时产生的不准确的显着性图，在预测标签不正确时产生的准确显着性图的罚款术语以及正式化术语对过于自信的显着性图时产生的罚款。实验表明分类性能，用户参与度和信任提高。
Convolutional neural networks (CNNs) are commonly used for image classification. Saliency methods are examples of approaches that can be used to interpret CNNs post hoc, identifying the most relevant pixels for a prediction following the gradients flow. Even though CNNs can correctly classify images, the underlying saliency maps could be erroneous in many cases. This can result in skepticism as to the validity of the model or its interpretation. We propose a novel approach for training trustworthy CNNs by penalizing parameter choices that result in inaccurate saliency maps generated during training. We add a penalty term for inaccurate saliency maps produced when the predicted label is correct, a penalty term for accurate saliency maps produced when the predicted label is incorrect, and a regularization term penalizing overly confident saliency maps. Experiments show increased classification performance, user engagement, and trust.
