Abstract Deep convolutional neural networks (CNNs) are the dominant technology in computer vision today. Much of the recent computer vision literature can be thought of as a competition to find the best architecture for vision within the deep convolutional framework. Despite all the effort invested in developing sophisticated convolutional architectures, however, it’s not clear how different from each other the best CNNs really are. This paper measures the similarity between two well-known CNNs, Inception and ResNet, in terms of the properties they extract from images. We find that the properties extracted by Inception are very similar to the properties extracted by ResNet, in the sense that either feature set can be well approximated by an affine transformation of the other. In particular, we find evidence that the information extracted from images by ResNet is also extracted by Inception, and in some cases may be more robustly extracted by Inception. In the other direction, most but not all of the information extracted by Inception is also extracted by ResNet. The similarity between Inception and ResNet features is surprising. Convolutional neural networks learn complex non-linear features of images, and the architectural differences between systems suggest that these non-linear functions should take different forms. Nonetheless, Inception and ResNet were trained on the same data set and seem to have learned to extract similar properties from images. In essence, their training algorithms hill-climb in totally different spaces, but find similar solutions. This suggests that for CNNs, the selection of the training set may be more important than the selection of the convolutional architecture. keyword: ResNet, Inception, CNN, Feature Evaluation, Feature Mapping.

中文翻译：

---

Inception 和 ResNet 功能（几乎）等效

摘要 深度卷积神经网络 (CNN) 是当今计算机视觉领域的主导技术。最近的许多计算机视觉文献都可以被认为是在深度卷积框架内寻找最佳视觉架构的竞赛。尽管在开发复杂的卷积架构上投入了大量精力，但尚不清楚最好的 CNN 之间到底有多大不同。本文根据它们从图像中提取的属性来衡量两个著名的 CNN（Inception 和 ResNet）之间的相似性。我们发现 Inception 提取的属性与 ResNet 提取的属性非常相似，从某种意义上说，任何一个特征集都可以通过另一个的仿射变换很好地近似。特别是，我们发现证据表明，ResNet 从图像中提取的信息也被 Inception 提取，并且在某些情况下，Inception 提取的信息可能更稳健。在另一个方向，Inception 提取的大部分但不是全部信息也被 ResNet 提取。Inception 和 ResNet 特征之间的相似性令人惊讶。卷积神经网络学习图像的复杂非线性特征，系统之间的架构差异表明这些非线性函数应该采用不同的形式。尽管如此，Inception 和 ResNet 是在相同的数据集上训练的，并且似乎已经学会了从图像中提取相似的属性。本质上，他们的训练算法在完全不同的空间爬山，但找到了相似的解决方案。这表明对于 CNN，训练集的选择可能比卷积架构的选择更重要。关键词：ResNet、Inception、CNN、特征评估、特征映射。