Copertina

Understanding when spatial transformer networks do not support invariance, and what to do about it

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Finnveden, Lukas, Jansson, Ylva, Lindeberg, Tony
Natura:	Preprint
Pubblicazione:	2020
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

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

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

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

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

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

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
di: Lindeberg, Tony
Pubblicazione: (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
di: Lindeberg, Tony
Pubblicazione: (2024)

Hybrid Lie semi-group and cascade structures for the generalized Gaussian derivative model for visual receptive fields
di: Lindeberg, Tony
Pubblicazione: (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
di: Lindeberg, Tony, et al.
Pubblicazione: (2025)

Sample what you cant compress
di: Birodkar, Vighnesh, et al.
Pubblicazione: (2024)

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

Discrete approximations of Gaussian smoothing and Gaussian derivatives
di: Lindeberg, Tony
Pubblicazione: (2023)

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

Do not trust what you trust: Miscalibration in Semi-supervised Learning
di: Mishra, Shambhavi, et al.
Pubblicazione: (2024)

Model Integrity when Unlearning with T2I Diffusion Models
di: Schioppa, Andrea, et al.
Pubblicazione: (2024)

TrashDet: Iterative Neural Architecture Search for Efficient Waste Detection
di: Tran, Tony, et al.
Pubblicazione: (2025)

A hierarchical loss and its problems when classifying non-hierarchically
di: Wu, Cinna, et al.
Pubblicazione: (2017)

Understanding vision transformer robustness through the lens of out-of-distribution detection
di: Kuang, Joey, et al.
Pubblicazione: (2026)

Mind the map! Accounting for existing map information when estimating online HDMaps from sensor
di: Sun, Rémy, et al.
Pubblicazione: (2023)

Finetuning CLIP to Reason about Pairwise Differences
di: Sam, Dylan, et al.
Pubblicazione: (2024)

ELASTIC: Efficient Once For All Iterative Search for Object Detection on Microcontrollers
di: Tran, Tony, et al.
Pubblicazione: (2025)

Structure-preserving contrastive learning for spatial time series
di: Jiao, Yiru, et al.
Pubblicazione: (2025)

Enhancing compact convolutional transformers with super attention
di: Leandre, Simpenzwe Honore, et al.
Pubblicazione: (2025)

Spatio-Temporal LLM: Reasoning about Environments and Actions
di: Zheng, Haozhen, et al.
Pubblicazione: (2025)

Scalable spatial point process models for forensic footwear analysis
di: Manna, Alokesh, et al.
Pubblicazione: (2026)

GeoAI Reproducibility and Replicability: a computational and spatial perspective
di: Li, Wenwen, et al.
Pubblicazione: (2024)

ChatHuman: Chatting about 3D Humans with Tools
di: Lin, Jing, et al.
Pubblicazione: (2024)

Rethinking Dataset Distillation: Hard Truths about Soft Labels
di: Dey, Priyam, et al.
Pubblicazione: (2026)

Improving MLLM Historical Record Extraction with Test-Time Image
di: Archibald, Taylor, et al.
Pubblicazione: (2025)

ILPO-NET: Network for the invariant recognition of arbitrary volumetric patterns in 3D
di: Zhemchuzhnikov, Dmitrii, et al.
Pubblicazione: (2024)

Benford's law: what does it say on adversarial images?
di: Zago, João G., et al.
Pubblicazione: (2021)

Cross-Validation Is All You Need: A Statistical Approach To Label Noise Estimation
di: Chen, Jianan, et al.
Pubblicazione: (2023)

Seeing the roads through the trees: A benchmark for modeling spatial dependencies with aerial imagery
di: Robinson, Caleb, et al.
Pubblicazione: (2024)

REDistill: Robust Estimator Distillation for Balancing Robustness and Efficiency
di: Tybl, Ondrej, et al.
Pubblicazione: (2026)

Deepfake Detection of Face Images based on a Convolutional Neural Network
di: Kroiß, Lukas, et al.
Pubblicazione: (2025)

Time-aware UNet and super-resolution deep residual networks for spatial downscaling
di: Sipilä, Mika, et al.
Pubblicazione: (2025)