The success of recent deep convolutional neural networks (CNNs) depends on learning hidden representations that can summarize the important factors of variation behind the data. In this work, we describe Network Dissection, a method that interprets networks by providing meaningful labels to their individual units. The proposed method quantifies the interpretability of CNN representations by evaluating the alignment between individual hidden units and visual semantic concepts. By identifying the best alignments, units are given interpretable labels ranging from colors, materials, textures, parts, objects and scenes. The method reveals that deep representations are more transparent and interpretable than they would be under a random equivalently powerful basis. We apply our approach to interpret and compare the latent representations of several network architectures trained to solve a wide range of supervised and self-supervised tasks. We then examine factors affecting the network interpretability such as the number of the training iterations, regularizations, different initialization parameters, as well as networks depth and width. Finally we show that the interpreted units can be used to provide explicit explanations of a given CNN prediction for an image. Our results highlight that interpretability is an important property of deep neural networks that provides new insights into what hierarchical structures can learn.

中文翻译：

---

通过网络剖析解释深层视觉表示


最近深度卷积神经网络（CNN）的成功取决于学习隐藏表示，这些表示可以总结数据背后变化的重要因素。在这项工作中，我们描述了网络剖析，这是一种通过为各个单元提供有意义的标签来解释网络的方法。该方法通过评估各个隐藏单元和视觉语义概念之间的对齐来量化 CNN 表示的可解释性。通过识别最佳对齐方式，单元会被赋予可解释的标签，包括颜色、材料、纹理、零件、物体和场景。该方法揭示了深度表示比在随机同等强大的基础下更加透明和可解释。我们应用我们的方法来解释和比较经过训练以解决各种监督和自监督任务的几种网络架构的潜在表示。然后，我们检查影响网络可解释性的因素，例如训练迭代次数、正则化、不同的初始化参数以及网络深度和宽度。最后，我们证明解释单元可用于为图像的给定 CNN 预测提供明确的解释。我们的结果强调，可解释性是深度神经网络的一个重要属性，它为层次结构可以学习的内容提供了新的见解。