论文标题
聚-CAM：卷积神经网络的高分辨率类激活图
Poly-CAM: High resolution class activation map for convolutional neural networks
论文作者
论文摘要
随着深度学习的发展，对可解释的AI的需求正在增加。从卷积神经网络中得出的显着图通常无法准确定位，图像特征是为网络预测合理的。这是因为这些地图要么是低分辨率的[Zhou等，2016]，要么是基于扰动的方法[Zeiler和Fergus，2014]，或者确实对应于广泛的峰值峰点，如梯度基于梯度的方法[Sundararajan等，2017，2017，Smilkov et al，2017]。相比之下，我们的工作建议将早期网络层的信息与后来层的信息相结合，以产生高分辨率类激活图，该图与以前的插入效果忠实度指标的竞争性竞争，同时在类别特异性特征本地化的精确度上超过了它的表现。
The need for Explainable AI is increasing with the development of deep learning. The saliency maps derived from convolutional neural networks generally fail in localizing with accuracy the image features justifying the network prediction. This is because those maps are either low-resolution as for CAM [Zhou et al., 2016], or smooth as for perturbation-based methods [Zeiler and Fergus, 2014], or do correspond to a large number of widespread peaky spots as for gradient-based approaches [Sundararajan et al., 2017, Smilkov et al., 2017]. In contrast, our work proposes to combine the information from earlier network layers with the one from later layers to produce a high resolution Class Activation Map that is competitive with the previous art in term of insertion-deletion faithfulness metrics, while outperforming it in term of precision of class-specific features localization.
