As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain

• URL: http://arxiv.org/abs/2307.10001v2
• Date: Wed, 15 May 2024 06:27:45 GMT
• Title: As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain
• Authors: Julia Grabinski, Janis Keuper, Margret Keuper,
• Abstract summary: Recent work in neural networks for image classification has seen a strong tendency towards increasing the spatial context. We propose a module for studying the effective filter size of convolutional neural networks. Our analysis shows that, although the proposed networks could learn very large convolution kernels, the learned filters are well localized and relatively small in practice.
• Score: 22.512062422338914
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent work in neural networks for image classification has seen a strong tendency towards increasing the spatial context. Whether achieved through large convolution kernels or self-attention, models scale poorly with the increased spatial context, such that the improved model accuracy often comes at significant costs. In this paper, we propose a module for studying the effective filter size of convolutional neural networks. To facilitate such a study, several challenges need to be addressed: 1) we need an effective means to train models with large filters (potentially as large as the input data) without increasing the number of learnable parameters 2) the employed convolution operation should be a plug-and-play module that can replace conventional convolutions in a CNN and allow for an efficient implementation in current frameworks 3) the study of filter sizes has to be decoupled from other aspects such as the network width or the number of learnable parameters 4) the cost of the convolution operation itself has to remain manageable i.e. we cannot naively increase the size of the convolution kernel. To address these challenges, we propose to learn the frequency representations of filter weights as neural implicit functions, such that the better scalability of the convolution in the frequency domain can be leveraged. Additionally, due to the implementation of the proposed neural implicit function, even large and expressive spatial filters can be parameterized by only a few learnable weights. Our analysis shows that, although the proposed networks could learn very large convolution kernels, the learned filters are well localized and relatively small in practice when transformed from the frequency to the spatial domain. We anticipate that our analysis of individually optimized filter sizes will allow for more efficient, yet effective, models in the future. https://github.com/GeJulia/NIFF.

Related papers

• Solving Large-scale Spatial Problems with Convolutional Neural Networks [88.31876586547848]
  We employ transfer learning to improve training efficiency for large-scale spatial problems. We propose that a convolutional neural network (CNN) can be trained on small windows of signals, but evaluated on arbitrarily large signals with little to no performance degradation.
  arXiv  Detail & Related papers  (2023-06-14T01:24:42Z)
• The Power of Linear Combinations: Learning with Random Convolutions [2.0305676256390934]
  Modern CNNs can achieve high test accuracies without ever updating randomly (spatial) convolution filters. These combinations of random filters can implicitly regularize the resulting operations. Although we only observe relatively small gains from learning $3times 3$ convolutions, the learning gains increase proportionally with kernel size.
  arXiv  Detail & Related papers  (2023-01-26T19:17:10Z)
• Variable Bitrate Neural Fields [75.24672452527795]
  We present a dictionary method for compressing feature grids, reducing their memory consumption by up to 100x. We formulate the dictionary optimization as a vector-quantized auto-decoder problem which lets us learn end-to-end discrete neural representations in a space where no direct supervision is available.
  arXiv  Detail & Related papers  (2022-06-15T17:58:34Z)
• Learning Versatile Convolution Filters for Efficient Visual Recognition [125.34595948003745]
  This paper introduces versatile filters to construct efficient convolutional neural networks. We conduct theoretical analysis on network complexity and an efficient convolution scheme is introduced. Experimental results on benchmark datasets and neural networks demonstrate that our versatile filters are able to achieve comparable accuracy as that of original filters.
  arXiv  Detail & Related papers  (2021-09-20T06:07:14Z)
• Global Filter Networks for Image Classification [90.81352483076323]
  We present a conceptually simple yet computationally efficient architecture that learns long-term spatial dependencies in the frequency domain with log-linear complexity. Our results demonstrate that GFNet can be a very competitive alternative to transformer-style models and CNNs in efficiency, generalization ability and robustness.
  arXiv  Detail & Related papers  (2021-07-01T17:58:16Z)
• Resolution learning in deep convolutional networks using scale-space theory [31.275270391367425]
  Resolution in deep convolutional neural networks (CNNs) is typically bounded by the receptive field size through filter sizes, and subsampling layers or strided convolutions on feature maps. We propose to do away with hard-coded resolution hyper- parameters and aim to learn the appropriate resolution from data. We use scale-space theory to obtain a self-similar parametrization of filters and make use of the N-Jet: a truncated Taylor series to approximate a filter by a learned combination of Gaussian derivative filters.
  arXiv  Detail & Related papers  (2021-06-07T08:23:02Z)
• Graph Neural Networks with Adaptive Frequency Response Filter [55.626174910206046]
  We develop a graph neural network framework AdaGNN with a well-smooth adaptive frequency response filter. We empirically validate the effectiveness of the proposed framework on various benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-26T19:31:21Z)
• Learning Sparse Filters in Deep Convolutional Neural Networks with a l1/l2 Pseudo-Norm [5.3791844634527495]
  Deep neural networks (DNNs) have proven to be efficient for numerous tasks, but come at a high memory and computation cost. Recent research has shown that their structure can be more compact without compromising their performance. We present a sparsity-inducing regularization term based on the ratio l1/l2 pseudo-norm defined on the filter coefficients.
  arXiv  Detail & Related papers  (2020-07-20T11:56:12Z)
• Dependency Aware Filter Pruning [74.69495455411987]
  Pruning a proportion of unimportant filters is an efficient way to mitigate the inference cost. Previous work prunes filters according to their weight norms or the corresponding batch-norm scaling factors. We propose a novel mechanism to dynamically control the sparsity-inducing regularization so as to achieve the desired sparsity.
  arXiv  Detail & Related papers  (2020-05-06T07:41:22Z)

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.