Cover Image

The problems with using STNs to align CNN feature maps

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Finnveden, Lukas, Jansson, Ylva, Lindeberg, Tony
Format:	Preprint
Published:	2020
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

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

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

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)

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

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

Video alignment using unsupervised learning of local and global features
by: Fakhfour, Niloufar, et al.
Published: (2023)

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)

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

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)

Model alignment using inter-modal bridges
by: Gholamzadeh, Ali, et al.
Published: (2025)

Base and Exponent Prediction in Mathematical Expressions using Multi-Output CNN
by: Salam, Md Laraib, et al.
Published: (2024)

CNN Mixture-of-Depths
by: Cakaj, Rinor, et al.
Published: (2024)

Human Fall Detection using Transfer Learning-based 3D CNN
by: Alam, Ekram, et al.
Published: (2025)

Retinal Disease Classification from Fundus Images using CNN Transfer Learning
by: Akram, Ali
Published: (2026)

Detection and Classification of Diseases in Multi-Crop Leaves using LSTM and CNN Models
by: Kanakala, Srinivas, et al.
Published: (2025)

Lemon and Orange Disease Classification using CNN-Extracted Features and Machine Learning Classifier
by: Arifin, Khandoker Nosiba, et al.
Published: (2024)

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

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

Texture image retrieval using a classification and contourlet-based features
by: Rouhafzay, Asal, et al.
Published: (2024)

LayerSync: Self-aligning Intermediate Layers
by: Haghighi, Yasaman, et al.
Published: (2025)

Closing the gap in multimodal medical representation alignment
by: Grassucci, Eleonora, et al.
Published: (2026)

FeatInv: Spatially resolved mapping from feature space to input space using conditional diffusion models
by: Neukirch, Nils, et al.
Published: (2025)

An Optimized Toolbox for Advanced Image Processing with Tsetlin Machine Composites
by: Grønningsæter, Ylva, et al.
Published: (2024)

CNN-based solution for mango classification in agricultural environments
by: Peón, Beatriz Díaz, et al.
Published: (2025)

Color Recognition in Challenging Lighting Environments: CNN Approach
by: Maitlo, Nizamuddin, et al.
Published: (2024)

Sparse components distinguish visual pathways & their alignment to neural networks
by: Marvi, Ammar I, et al.
Published: (2025)

Hybrid CNN with Chebyshev Polynomial Expansion for Medical Image Analysis
by: Roy, Abhinav, et al.
Published: (2025)

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
by: Lindeberg, Tony, et al.
Published: (2025)

Rad4XCNN: a new agnostic method for post-hoc global explanation of CNN-derived features by means of radiomics
by: Prinzi, Francesco, et al.
Published: (2024)

Multi-feature Reconstruction Network using Crossed-mask Restoration for Unsupervised Industrial Anomaly Detection
by: Wang, Junpu, et al.
Published: (2024)

EaqVLA: Encoding-aligned Quantization for Vision-Language-Action Models
by: Jiang, Feng, et al.
Published: (2025)

Can multimodal representation learning by alignment preserve modality-specific information?
by: Thoreau, Romain, et al.
Published: (2025)

FeatMap: Understanding image manipulation in the feature space and its implications for feature space geometry
by: Krey, Elias B., et al.
Published: (2026)

A Novel CNN Gradient Boosting Ensemble for Guava Disease Detection
by: Rijon, Tamim Ahasan, et al.
Published: (2025)

Why CNN Features Are not Gaussian: A Statistical Anatomy of Deep Representations
by: Chapman, David, et al.
Published: (2024)

Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling
by: Byun, Min Sik, et al.
Published: (2025)