论文标题
最终完全连接层的解释
An interpretation of the final fully connected layer
论文作者
论文摘要
近年来，神经网络已经达到了各种任务的最先进的准确性，但是对产生产量的解释仍然很困难。在这项工作中，我们试图提供一种方法，以了解图像分类模型中最终完全连接的层中学习的权重。我们通过在RL中的政策梯度目标与受监督的学习目标之间建立联系来激励我们的方法。我们建议，常用的基于跨熵的监督学习目标可以被视为政策梯度目标的特殊情况。使用此见解，我们提出了一种方法，以找到图像中最歧视性和混乱的部分。我们的方法没有对神经网络成就的任何事先假设，并且计算成本较低。我们将我们的方法应用于公开可用的预训练模型，并报告生成的结果。
In recent years neural networks have achieved state-of-the-art accuracy for various tasks but the the interpretation of the generated outputs still remains difficult. In this work we attempt to provide a method to understand the learnt weights in the final fully connected layer in image classification models. We motivate our method by drawing a connection between the policy gradient objective in RL and supervised learning objective. We suggest that the commonly used cross entropy based supervised learning objective can be regarded as a special case of the policy gradient objective. Using this insight we propose a method to find the most discriminative and confusing parts of an image. Our method does not make any prior assumption about neural network achitecture and has low computational cost. We apply our method on publicly available pre-trained models and report the generated results.
