Spectral Leakage and Rethinking the Kernel Size in CNNs

• URL: http://arxiv.org/abs/2101.10143v1
• Date: Mon, 25 Jan 2021 14:49:29 GMT
• Title: Spectral Leakage and Rethinking the Kernel Size in CNNs
• Authors: Nergis Tomen, Jan van Gemert
• Abstract summary: We show that the small size of CNN kernels make them susceptible to spectral leakage. We demonstrate improved classification accuracy over baselines with conventional $3times 3$ kernels. We also show that CNNs employing the Hamming window display increased robustness against certain types of adversarial attacks.
• Score: 10.432041176720842
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Convolutional layers in CNNs implement linear filters which decompose the input into different frequency bands. However, most modern architectures neglect standard principles of filter design when optimizing their model choices regarding the size and shape of the convolutional kernel. In this work, we consider the well-known problem of spectral leakage caused by windowing artifacts in filtering operations in the context of CNNs. We show that the small size of CNN kernels make them susceptible to spectral leakage, which may induce performance-degrading artifacts. To address this issue, we propose the use of larger kernel sizes along with the Hamming window function to alleviate leakage in CNN architectures. We demonstrate improved classification accuracy over baselines with conventional $3\times 3$ kernels, on multiple benchmark datasets including Fashion-MNIST, CIFAR-10, CIFAR-100 and ImageNet, via the simple use of a standard window function in convolutional layers. Finally, we show that CNNs employing the Hamming window display increased robustness against certain types of adversarial attacks.

Related papers

• Tensor network compressibility of convolutional models [0.0]
  We assess how textittruncating the convolution kernels of textitdense (untensorized) CNNs impact their accuracy. We found that kernels could often be truncated along several cuts resulting in significant loss in kernel norm but not in classification accuracy.
  arXiv  Detail & Related papers  (2024-03-21T13:12:33Z)
• CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective [2.7195102129095003]
  Large kernel CNNs have been reported to perform well in downstream vision tasks as well as in classification performance. We revisit the performance of large kernel CNNs in downstream task, focusing on the weakly supervised object localization task. Our study compares the modern large kernel CNNs ConvNeXt, RepLKNet, and SLaK to test the validity of the naive expectation that ERF size is important for improving downstream task performance.
  arXiv  Detail & Related papers  (2024-03-11T12:48:22Z)
• PICNN: A Pathway towards Interpretable Convolutional Neural Networks [12.31424771480963]
  We introduce a novel pathway to alleviate the entanglement between filters and image classes. We use the Bernoulli sampling to generate the filter-cluster assignment matrix from a learnable filter-class correspondence matrix. We evaluate the effectiveness of our method on ten widely used network architectures.
  arXiv  Detail & Related papers  (2023-12-19T11:36:03Z)
• Scaling Spherical CNNs [19.735829027026902]
  We show how spherical convolutions can be scaled for much larger problems. Experiments show our larger spherical CNNs reach state-of-the-art on several targets of the QM9 molecular benchmark.
  arXiv  Detail & Related papers  (2023-06-08T17:59:08Z)
• Towards a General Purpose CNN for Long Range Dependencies in $\mathrm{N}$D [49.57261544331683]
  We propose a single CNN architecture equipped with continuous convolutional kernels for tasks on arbitrary resolution, dimensionality and length without structural changes. We show the generality of our approach by applying the same CCNN to a wide set of tasks on sequential (1$mathrmD$) and visual data (2$mathrmD$) Our CCNN performs competitively and often outperforms the current state-of-the-art across all tasks considered.
  arXiv  Detail & Related papers  (2022-06-07T15:48:02Z)
• Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs [148.0476219278875]
  We revisit large kernel design in modern convolutional neural networks (CNNs) Inspired by recent advances of vision transformers (ViTs), in this paper, we demonstrate that using a few large convolutional kernels instead of a stack of small kernels could be a more powerful paradigm. We propose RepLKNet, a pure CNN architecture whose kernel size is as large as 31x31, in contrast to commonly used 3x3.
  arXiv  Detail & Related papers  (2022-03-13T17:22:44Z)
• Content-Aware Convolutional Neural Networks [98.97634685964819]
  Convolutional Neural Networks (CNNs) have achieved great success due to the powerful feature learning ability of convolution layers. We propose a Content-aware Convolution (CAC) that automatically detects the smooth windows and applies a 1x1 convolutional kernel to replace the original large kernel.
  arXiv  Detail & Related papers  (2021-06-30T03:54:35Z)
• SpectralNET: Exploring Spatial-Spectral WaveletCNN for Hyperspectral Image Classification [0.0]
  Hyperspectral Image (HSI) classification using Convolutional Neural Networks (CNN) is widely found in the current literature. We propose SpectralNET, a wavelet CNN, which is a variation of 2D CNN for multi-resolution HSI classification.
  arXiv  Detail & Related papers  (2021-04-01T08:45:15Z)
• The Mind's Eye: Visualizing Class-Agnostic Features of CNNs [92.39082696657874]
  We propose an approach to visually interpret CNN features given a set of images by creating corresponding images that depict the most informative features of a specific layer. Our method uses a dual-objective activation and distance loss, without requiring a generator network nor modifications to the original model.
  arXiv  Detail & Related papers  (2021-01-29T07:46:39Z)
• ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution [57.635467829558664]
  We introduce a structural regularization across convolutional kernels in a CNN. We show that CNNs now maintain performance with dramatic reduction in parameters and computations.
  arXiv  Detail & Related papers  (2020-09-04T20:41:47Z)
• Approximation and Non-parametric Estimation of ResNet-type Convolutional Neural Networks [52.972605601174955]
  We show a ResNet-type CNN can attain the minimax optimal error rates in important function classes. We derive approximation and estimation error rates of the aformentioned type of CNNs for the Barron and H"older classes.
  arXiv  Detail & Related papers  (2019-03-24T19:42:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.