Modelling and analysis of the 8 filters from the "master key filters hypothesis" for depthwise-separable deep networks in relation to idealized receptive fields based on scale-space theory

• URL: http://arxiv.org/abs/2509.12746v1
• Date: Tue, 16 Sep 2025 07:04:45 GMT
• Title: Modelling and analysis of the 8 filters from the "master key filters hypothesis" for depthwise-separable deep networks in relation to idealized receptive fields based on scale-space theory
• Abstract summary: We first compute spatial spread measures in terms of weighted mean values and weighted variances of the absolute values of the learned filters.<n>We then model the clustered master key filters'' in terms of difference operators applied to a spatial smoothing operation.
• Score: 7.990816079551592
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper presents the results of analysing and modelling a set of 8 ``master key filters'', which have been extracted by applying a clustering approach to the receptive fields learned in depthwise-separable deep networks based on the ConvNeXt architecture. For this purpose, we first compute spatial spread measures in terms of weighted mean values and weighted variances of the absolute values of the learned filters, which support the working hypotheses that: (i) the learned filters can be modelled by separable filtering operations over the spatial domain, and that (ii) the spatial offsets of the those learned filters that are non-centered are rather close to half a grid unit. Then, we model the clustered ``master key filters'' in terms of difference operators applied to a spatial smoothing operation in terms of the discrete analogue of the Gaussian kernel, and demonstrate that the resulting idealized models of the receptive fields show good qualitative similarity to the learned filters. This modelling is performed in two different ways: (i) using possibly different values of the scale parameters in the coordinate directions for each filter, and (ii) using the same value of the scale parameter in both coordinate directions. Then, we perform the actual model fitting by either (i) requiring spatial spread measures in terms of spatial variances of the absolute values of the receptive fields to be equal, or (ii) minimizing the discrete $l_1$- or $l_2$-norms between the idealized receptive field models and the learned filters. Complementary experimental results then demonstrate the idealized models of receptive fields have good predictive properties for replacing the learned filters by idealized filters in depthwise-separable deep networks, thus showing that the learned filters in depthwise-separable deep networks can be well approximated by discrete scale-space filters.

Related papers

• The Quest for Universal Master Key Filters in DS-CNNs [52.091987605762135]
  We find 8 universal filters that depthwise separable convolutional networks inherently converge to.<n>Our analysis reveals these filters are predominantly linear shifts (ax+b) of our discovered universal set.<n>Remarkably, networks with these 8 unique frozen filters achieve over 80% ImageNet accuracy.
  arXiv  Detail & Related papers  (2025-09-15T09:10:13Z)
• Learning Optimal Filters Using Variational Inference [0.3749861135832072]
  We present a framework for learning a parameterized analysis map for filtering systems.<n>In principle this can lead to a better approximation of the filtering distribution, and hence smaller bias.<n>We show that this methodology can be used to learn the gain matrix, in an affine analysis map, for filtering linear and nonlinear dynamical systems.
  arXiv  Detail & Related papers  (2024-06-26T04:51:14Z)
• Closed-form Filtering for Non-linear Systems [83.91296397912218]
  We propose a new class of filters based on Gaussian PSD Models, which offer several advantages in terms of density approximation and computational efficiency. We show that filtering can be efficiently performed in closed form when transitions and observations are Gaussian PSD Models. Our proposed estimator enjoys strong theoretical guarantees, with estimation error that depends on the quality of the approximation and is adaptive to the regularity of the transition probabilities.
  arXiv  Detail & Related papers  (2024-02-15T08:51:49Z)
• Decomposed Guided Dynamic Filters for Efficient RGB-Guided Depth Completion [46.04264366475848]
  RGB-guided depth completion aims at predicting dense depth maps from sparse depth measurements and corresponding RGB images. Guided dynamic filters generate spatially-variant depth-wise separable convolutional filters from RGB features to guide depth features. We propose to decompose the guided dynamic filters into a spatially-shared component multiplied by content-adaptive adaptors at each spatial location.
  arXiv  Detail & Related papers  (2023-09-05T08:37:58Z)
• Computational Doob's h-transforms for Online Filtering of Discretely Observed Diffusions [65.74069050283998]
  We propose a computational framework to approximate Doob's $h$-transforms. The proposed approach can be orders of magnitude more efficient than state-of-the-art particle filters.
  arXiv  Detail & Related papers  (2022-06-07T15:03:05Z)
• Deep Learning for the Benes Filter [91.3755431537592]
  We present a new numerical method based on the mesh-free neural network representation of the density of the solution of the Benes model. We discuss the role of nonlinearity in the filtering model equations for the choice of the domain of the neural network.
  arXiv  Detail & Related papers  (2022-03-09T14:08:38Z)
• 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)
• DNN-Based Topology Optimisation: Spatial Invariance and Neural Tangent Kernel [7.106986689736828]
  We study the SIMP method with a density field generated by a fully-connected neural network, taking the coordinates as inputs. We show that the use of DNNs leads to a filtering effect similar to traditional filtering techniques for SIMP, with a filter described by the Neural Tangent Kernel (NTK)
  arXiv  Detail & Related papers  (2021-06-10T12:49:55Z)
• 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)
• Unsharp Mask Guided Filtering [53.14430987860308]
  The goal of this paper is guided image filtering, which emphasizes the importance of structure transfer during filtering. We propose a new and simplified formulation of the guided filter inspired by unsharp masking. Our formulation enjoys a filtering prior to a low-pass filter and enables explicit structure transfer by estimating a single coefficient.
  arXiv  Detail & Related papers  (2021-06-02T19:15:34Z)

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.