Hybrid Lie semi-group and cascade structures for the generalized Gaussian derivative model for visual receptive fields

• URL: http://arxiv.org/abs/2509.15748v1
• Date: Fri, 19 Sep 2025 08:23:44 GMT
• Title: Hybrid Lie semi-group and cascade structures for the generalized Gaussian derivative model for visual receptive fields
• Authors: Tony Lindeberg,
• Abstract summary: Receptive field responses may be strongly influenced by geometric image transformations.<n>One way of handling this is by basing the vision system on covariant receptive field families.<n>This paper addresses the problem of deriving relationships between spatial and Lietemporal receptive field responses.
• Score: 5.381004207943597
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Because of the variabilities of real-world image structures under the natural image transformations that arise when observing similar objects or spatio-temporal events under different viewing conditions, the receptive field responses computed in the earliest layers of the visual hierarchy may be strongly influenced by such geometric image transformations. One way of handling this variability is by basing the vision system on covariant receptive field families, which expand the receptive field shapes over the degrees of freedom in the image transformations. This paper addresses the problem of deriving relationships between spatial and spatio-temporal receptive field responses obtained for different values of the shape parameters in the resulting multi-parameter families of receptive fields. For this purpose, we derive both (i) infinitesimal relationships, roughly corresponding to a combination of notions from semi-groups and Lie groups, as well as (ii) macroscopic cascade smoothing properties, which describe how receptive field responses at coarser spatial and temporal scales can be computed by applying smaller support incremental filters to the output from corresponding receptive fields at finer spatial and temporal scales, structurally related to the notion of Lie algebras, although with directional preferences. The presented results provide (i) a deeper understanding of the relationships between spatial and spatio-temporal receptive field responses for different values of the filter parameters, which can be used for both (ii) designing more efficient schemes for computing receptive field responses over populations of multi-parameter families of receptive fields, as well as (iii)~formulating idealized theoretical models of the computations of simple cells in biological vision.

Related papers

• Quantum fields from real-time ensemble dynamics [6.0523316051636025]
  We formulate quantum fields in a real-time Schrdinger-picture framework.<n>Within this formulation, the wave $[,t]$ encodes a first-order, causal ensemble dynamics on configuration space.<n> Entanglement, scattering, and conformal field amplitudes emerge as distinct projections of the same underlying ensemble theory.
  arXiv  Detail & Related papers  (2026-02-04T05:40:38Z)
• Generalized Linear Mode Connectivity for Transformers [87.32299363530996]
  A striking phenomenon is linear mode connectivity (LMC), where independently trained models can be connected by low- or zero-loss paths.<n>Prior work has predominantly focused on neuron re-ordering through permutations, but such approaches are limited in scope.<n>We introduce a unified framework that captures four symmetry classes: permutations, semi-permutations, transformations, and general invertible maps.<n>This generalization enables, for the first time, the discovery of low- and zero-barrier linear paths between independently trained Vision Transformers and GPT-2 models.
  arXiv  Detail & Related papers  (2025-06-28T01:46:36Z)
• ARC-Flow : Articulated, Resolution-Agnostic, Correspondence-Free Matching and Interpolation of 3D Shapes Under Flow Fields [4.706075725469252]
  This work presents a unified framework for the unsupervised prediction of physically plausibles between two 3D articulated shapes.<n>Interpolation is modelled as a diffeomorphic transformation using a smooth, time-varying flow field governed by Neural Ordinary Differential Equations (ODEs)<n>Correspondence is recovered using an efficient Varifold formulation, that is effective on high-fidelity surfaces with differing parameterisations.
  arXiv  Detail & Related papers  (2025-03-04T13:28:05Z)
• Relationships between the degrees of freedom in the affine Gaussian derivative model for visual receptive fields and 2-D affine image transformations, with application to covariance properties of simple cells in the primary visual cortex [0.5439020425819]
  This paper presents a theoretical analysis of relationships between the degrees of freedom in 2-D spatial affine image transformations and the degrees of freedom in the affine Gaussian derivative model for visual receptive fields.<n>We consider whether we could regard the biological receptive fields in the primary visual cortex of higher mammals as being able to span the degrees of freedom of 2-D spatial affine transformations.
  arXiv  Detail & Related papers  (2024-11-08T16:24:20Z)
• Relative Representations: Topological and Geometric Perspectives [53.88896255693922]
  Relative representations are an established approach to zero-shot model stitching.<n>We introduce a normalization procedure in the relative transformation, resulting in invariance to non-isotropic rescalings and permutations.<n>Second, we propose to deploy topological densification when fine-tuning relative representations, a topological regularization loss encouraging clustering within classes.
  arXiv  Detail & Related papers  (2024-09-17T08:09:22Z)
• Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration [59.062085785106234]
  This article presents a general Bayesian learning framework for multi-modal groupwise image registration.<n>We propose a novel hierarchical variational auto-encoding architecture to realise the inference procedure of the latent variables.<n>Experiments were conducted to validate the proposed framework, including four different datasets from cardiac, brain, and abdominal medical images.
  arXiv  Detail & Related papers  (2024-01-04T08:46:39Z)
• Unified theory for joint covariance properties under geometric image transformations for spatio-temporal receptive fields according to the generalized Gaussian derivative model for visual receptive fields [0.5439020425819]
  We show how the parameters of receptive fields need to be transformed, in order to match the output from receptive fields under atemporal image relations.<n>We conclude with geometric analysis, showing how derived joint covariance properties make it possible to relate or match receptive field responses.
  arXiv  Detail & Related papers  (2023-11-17T14:10:55Z)
• Image Synthesis via Semantic Composition [74.68191130898805]
  We present a novel approach to synthesize realistic images based on their semantic layouts. It hypothesizes that for objects with similar appearance, they share similar representation. Our method establishes dependencies between regions according to their appearance correlation, yielding both spatially variant and associated representations.
  arXiv  Detail & Related papers  (2021-09-15T02:26:07Z)
• Joint Network Topology Inference via Structured Fusion Regularization [70.30364652829164]
  Joint network topology inference represents a canonical problem of learning multiple graph Laplacian matrices from heterogeneous graph signals. We propose a general graph estimator based on a novel structured fusion regularization. We show that the proposed graph estimator enjoys both high computational efficiency and rigorous theoretical guarantee.
  arXiv  Detail & Related papers  (2021-03-05T04:42:32Z)
• Joint Estimation of Image Representations and their Lie Invariants [57.3768308075675]
  Images encode both the state of the world and its content. The automatic extraction of this information is challenging because of the high-dimensionality and entangled encoding inherent to the image representation. This article introduces two theoretical approaches aimed at the resolution of these challenges.
  arXiv  Detail & Related papers  (2020-12-05T00:07:41Z)

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.