paper-with-me

홈 › Papers

What do CNNs Learn in the First Layer and Why? A Linear Systems Perspective

2022-06-06 · Rhea Chowers, Yair Weiss

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.

📄 PDF Abstract BibTeX arXiv:2206.02454

Code (1)

RheaChowers/first-layer-representations 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Residual Connection 설명 없음
Average Pooling 설명 없음
Batch Normalization 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…

Similar Papers 제목 키워드 기반

Can Attention Enable MLPs To Catch Up With CNNs?

2021-05-31 · Meng-Hao Guo, Zheng-Ning Liu, Tai-Jiang Mu, Dun Liang 외

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

2024-10-14 · Weronika Ormaniec, Felix Dangel, Sidak Pal Singh

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

2018-11-05 · NeurIPS 2019 12 · Taco Cohen, Mario Geiger, Maurice Weiler

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 Classification

TraNCE: Transformative Non-linear Concept Explainer for CNNs

2025-03-26 · Ugochukwu Ejike Akpudo, Yongsheng Gao, Jun Zhou, Andrew Lewis

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

2017-03-20 · Kaicheng Yu, Mathieu Salzmann

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