Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lindeberg, Tony, Babaiee, Zahra, Kiasari, Peyman M.
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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
by: Lindeberg, Tony
Published: (2023)

Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models
by: Babaiee, Zahra, et al.
Published: (2025)

The Master Key Filters Hypothesis: Deep Filters Are General
by: Babaiee, Zahra, et al.
Published: (2024)

Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields
by: Babaiee, Zahra, et al.
Published: (2024)

Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels
by: Babaiee, Zahra, et al.
Published: (2024)

Hybrid Lie semi-group and cascade structures for the generalized Gaussian derivative model for visual receptive fields
by: Lindeberg, Tony
Published: (2025)

Covariant spatio-temporal receptive fields for spiking neural networks
by: Pedersen, Jens Egholm, et al.
Published: (2024)

Provably scale-covariant continuous hierarchical networks based on scale-normalized differential expressions coupled in cascade
by: Lindeberg, Tony
Published: (2019)

Approximation properties relative to continuous scale space for hybrid discretizations of Gaussian derivative operators
by: Lindeberg, Tony
Published: (2024)

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
by: Lindeberg, Tony
Published: (2024)

Do the receptive fields in the primary visual cortex span a variability over the degree of elongation of the receptive fields?
by: Lindeberg, Tony
Published: (2024)

Scale-covariant and scale-invariant Gaussian derivative networks
by: Lindeberg, Tony
Published: (2020)

Direction and speed selectivity properties for spatio-temporal receptive fields according to the generalized Gaussian derivative model for visual receptive fields
by: Lindeberg, Tony
Published: (2025)

Provably scale-covariant networks from oriented quasi quadrature measures in cascade
by: Lindeberg, Tony
Published: (2019)

On sources to variabilities of simple cells in the primary visual cortex: A principled theory for the interaction between geometric image transformations and receptive field responses
by: Lindeberg, Tony
Published: (2025)

Scale generalisation properties of extended scale-covariant and scale-invariant Gaussian derivative networks on image datasets with spatial scaling variations
by: Perzanowski, Andrzej, et al.
Published: (2024)

Orientation selectivity properties for the affine Gaussian derivative and the affine Gabor models for visual receptive fields
by: Lindeberg, Tony
Published: (2023)

Exploring the ability of CNNs to generalise to previously unseen scales over wide scale ranges
by: Jansson, Ylva, et al.
Published: (2020)

The Quest for Universal Master Key Filters in DS-CNNs
by: Babaiee, Zahra, et al.
Published: (2025)

Scale-invariant Gaussian derivative residual networks
by: Perzanowski, Andrzej, et al.
Published: (2026)

On filter design in deep convolutional neural network
by: Hirani, Gaurav, et al.
Published: (2024)

Discrete approximations of Gaussian smoothing and Gaussian derivatives
by: Lindeberg, Tony
Published: (2023)

Are Programming Paradigms Paradigms? A Critical Examination of Floyd's Appropriation of Kuhn's Philosophy
by: Kiasari, Peyman M.
Published: (2025)

Understanding when spatial transformer networks do not support invariance, and what to do about it
by: Finnveden, Lukas, et al.
Published: (2020)

The problems with using STNs to align CNN feature maps
by: Finnveden, Lukas, et al.
Published: (2020)

Advanced deep architecture pruning using single filter performance
by: Tzach, Yarden, et al.
Published: (2025)

Orientation selectivity properties for integrated affine quasi quadrature models of complex cells
by: Lindeberg, Tony
Published: (2025)

Time-causal and time-recursive wavelets
by: Lindeberg, Tony
Published: (2025)

A time-causal and time-recursive analogue of the Gabor transform
by: Lindeberg, Tony
Published: (2023)

Learning deep illumination-robust features from multispectral filter array images
by: Amziane, Anis
Published: (2024)

A self-supervised learning approach to deep filter banks for texture recognition
by: Florindo, Joao B., et al.
Published: (2026)

Inability of spatial transformations of CNN feature maps to support invariant recognition
by: Jansson, Ylva, et al.
Published: (2020)

Adaptive receptive field-based spatial-frequency feature reconstruction network for few-shot fine-grained image classification
by: Zhang, Linyue, et al.
Published: (2026)

Accurate and lightweight dehazing via multi-receptive-field non-local network and novel contrastive regularization
by: He, Zewei, et al.
Published: (2023)

High-pass filtered fidelity-imposed network edit (HP-FINE) for robust quantitative susceptibility mapping from high-pass filtered phase
by: Zhang, Jinwei, et al.
Published: (2023)

Multi-scale frequency separation network for image deblurring
by: Zhang, Yanni, et al.
Published: (2022)

Patch-based adaptive temporal filter and residual evaluation
by: Zhao, Weiying, et al.
Published: (2024)

Neighborhood filters and the decreasing rearrangement
by: Galiano, Gonzalo, et al.
Published: (2013)

Improving trajectory continuity in drone-based crowd monitoring using a set of minimal-cost techniques and deep discriminative correlation filters
by: Ptak, Bartosz, et al.
Published: (2025)

PARF-Net: integrating pixel-wise adaptive receptive fields into hybrid Transformer-CNN network for medical image segmentation
by: Ma, Xu, et al.
Published: (2025)