What do CNNs Learn in the First Layer and Why? A Linear Systems Perspective
It has previously been reported that the representation that is learned in the first layer of deep Convolutional Neural Networks (CNNs) is highly consistent across initializations and architectures. In this work, we quantify this consistency by considering the first layer as a filter bank and measuring its energy distribution. We find that the energy distribution is very different from that of the initial weights and is remarkably consistent across random initializations, datasets, architectures and even when the CNNs are trained with random labels. In order to explain this consistency, we derive an analytical formula for the energy profile of linear CNNs and show that this profile is mostly dictated by the second order statistics of image patches in the training set and it will approach a whitening transformation when the number of iterations goes to infinity. Finally, we show that this formula for linear CNNs also gives an excellent fit for the energy profiles learned by commonly used nonlinear CNNs such as ResNet and VGG, and that the first layer of these CNNs indeed perform approximate whitening of their inputs.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Can Attention Enable MLPs To Catch Up With CNNs?
In the first week of May, 2021, researchers from four different institutions: Google, Tsinghua University, Oxford University and Facebook, shared their latest work [16, 7, 12, 17] on arXiv.org almost at the same time, ea…
What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis
The Transformer architecture has inarguably revolutionized deep learning, overtaking classical architectures like multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs). At its core, the attention block …
A General Theory of Equivariant CNNs on Homogeneous Spaces
We present a general theory of Group equivariant Convolutional Neural Networks (G-CNNs) on homogeneous spaces such as Euclidean space and the sphere. Feature maps in these networks represent fields on a homogeneous base …
General ClassificationTraNCE: Transformative Non-linear Concept Explainer for CNNs
Convolutional neural networks (CNNs) have succeeded remarkably in various computer vision tasks. However, they are not intrinsically explainable. While the feature-level understanding of CNNs reveals where the models loo…
Second-order Convolutional Neural Networks
Convolutional Neural Networks (CNNs) have been successfully applied to many computer vision tasks, such as image classification. By performing linear combinations and element-wise nonlinear operations, these networks can…
image-classificationImage Classification