Despite the state-of-the-art performance of deep convolutional neural networks, they are susceptible to bias and malfunction in unseen situations. Moreover, the complex computation behind their reasoning is not human-understandable to develop trust. External explainer methods have tried to interpret network decisions in a human-understandable way, but they are accused of fallacies due to their assumptions and simplifications. On the other side, the inherent self-interpretability of models, while being more robust to the mentioned fallacies, cannot be applied to the already trained models. In this work, we propose a new attention-based pooling layer, called Local Attention Pooling (LAP), that accomplishes self-interpretability and the possibility for knowledge injection without performance loss. The module is easily pluggable into any convolutional neural network, even the already trained ones. We have defined a weakly supervised training scheme to learn the distinguishing features in decision-making without depending on experts' annotations. We verified our claims by evaluating several LAP-extended models on two datasets, including ImageNet. The proposed framework offers more valid human-understandable and faithful-to-the-model interpretations than the commonly used white-box explainer methods.

翻译：尽管深度卷积神经网络具有最先进的性能，但它们在未见场景中容易产生偏差和故障。此外，其推理背后的复杂计算难以被人类理解以建立信任。外部解释方法试图以人类可理解的方式解释网络决策，但由于其假设和简化而受到质疑。另一方面，模型固有的自解释性虽然对上述谬误更具鲁棒性，但无法应用于已训练的模型。本文提出一种新的基于注意力的池化层——局部注意力池化（LAP），该模块在不损失性能的情况下实现自解释性并支持知识注入。该模块可轻松嵌入任何卷积神经网络，甚至包括已训练的模型。我们定义了一种弱监督训练方案，用于学习决策过程中的区分性特征，而无需依赖专家标注。通过在包括ImageNet在内的两个数据集上评估多个LAP扩展模型，我们验证了上述主张。与常用的白盒解释方法相比，所提框架提供了更有效、更符合人类理解且忠于模型本体的解释。