paper-with-me

홈 › Papers

The Singular Values of Convolutional Layers

2018-05-26 · ICLR 2019 5 · Hanie Sedghi, Vineet Gupta, Philip M. Long

We characterize the singular values of the linear transformation associated with a standard 2D multi-channel convolutional layer, enabling their efficient computation. This characterization also leads to an algorithm for projecting a convolutional layer onto an operator-norm ball. We show that this is an effective regularizer; for example, it improves the test error of a deep residual network using batch normalization on CIFAR-10 from 6.2\% to 5.3\%.

📄 PDF Abstract BibTeX arXiv:1805.10408

Code (1)

brain-research/conv-sv tf

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Towards Practical Control of Singular Values of Convolutional Layers

2022-11-24 · Alexandra Senderovich, Ekaterina Bulatova, Anton Obukhov, Maxim Rakhuba

In general, convolutional neural networks (CNNs) are easy to train, but their essential properties, such as generalization error and adversarial robustness, are hard to control. Recent research demonstrated that singular…

Adversarial Robustness

A Frobenius norm regularization method for convolutional kernels to avoid unstable gradient problem

2019-07-25 · Pei-Chang Guo

Convolutional neural network is a very important model of deep learning. It can help avoid the exploding/vanishing gradient problem and improve the generalizability of a neural network if the singular values of the Jacob…

Asymptotic Singular Value Distribution of Linear Convolutional Layers

2020-06-12 · Xinping Yi

In convolutional neural networks, the linear transformation of multi-channel two-dimensional convolutional layers with linear convolution is a block matrix with doubly Toeplitz blocks. Although a "wrapping around" operat…

ManifoldFlow: SPD-Relaxed Stiefel Layers with Learnable Singular Spectrum

2026-07-05 · Haiwen Yi, Xinyuan Song arxiv

Orthogonal and Stiefel layers give neural weights exact spectral control, but they also impose a strong modeling constraint: all represented singular values are fixed at one. Many settings that benefit from an orthonorma…

The SVD of Convolutional Weights: A CNN Interpretability Framework

2022-08-14 · Brenda Praggastis, Davis Brown, Carlos Ortiz Marrero, Emilie Purvine 외

Deep neural networks used for image classification often use convolutional filters to extract distinguishing features before passing them to a linear classifier. Most interpretability literature focuses on providing sema…

image-classificationImage Classification