Image de couverture de livre

Harmformer: Harmonic Networks Meet Transformers for Continuous Roto-Translation Equivariance

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Karella, Tomáš, Harmanec, Adam, Kotera, Jan, Blažek, Jan, Šroubek, Filip
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

RING#: PR-by-PE Global Localization with Roto-translation Equivariant Gram Learning
par: Lu, Sha, et autres
Publié: (2024)

Material Fingerprinting: Identifying and Predicting Perceptual Attributes of Material Appearance
par: Filip, Jiri, et autres
Publié: (2024)

Enhancing Image Restoration Transformer via Adaptive Translation Equivariance
par: Hu, JiaKui, et autres
Publié: (2025)

Translation-Equivariance of Normalization Layers and Aliasing in Convolutional Neural Networks
par: Scanvic, Jérémy, et autres
Publié: (2025)

Diffeomorphism-Equivariant Neural Networks
par: Oettinger, Josephine Elisabeth, et autres
Publié: (2026)

Deep Continuous Networks
par: Tomen, Nergis, et autres
Publié: (2024)

RMT: Retentive Networks Meet Vision Transformers
par: Fan, Qihang, et autres
Publié: (2023)

DiffHarmony: Latent Diffusion Model Meets Image Harmonization
par: Zhou, Pengfei, et autres
Publié: (2024)

Learning to Adapt to Position Bias in Vision Transformer Classifiers
par: Bruintjes, Robert-Jan, et autres
Publié: (2025)

StyleGAN3: Generative Networks for Improving the Equivariance of Translation and Rotation
par: Zhu, Tianlei, et autres
Publié: (2023)

Vanilla Group Equivariant Vision Transformer: Simple and Effective
par: Fu, Jiahong, et autres
Publié: (2026)

Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers
par: Pardyl, Adam, et autres
Publié: (2023)

Leveraging Point Transformers for Detecting Anatomical Landmarks in Digital Dentistry
par: Kubík, Tibor, et autres
Publié: (2025)

Equivariant Multiscale Learned Invertible Reconstruction for Cone Beam CT
par: Moriakov, Nikita, et autres
Publié: (2024)

Capsule Network Projectors are Equivariant and Invariant Learners
par: Everett, Miles, et autres
Publié: (2024)

SERUM: Simple, Efficient, Robust, and Unifying Marking for Diffusion-based Image Generation
par: Kociszewski, Jan, et autres
Publié: (2026)

PixOOD: Pixel-Level Out-of-Distribution Detection
par: Vojíř, Tomáš, et autres
Publié: (2024)

MambaVision: A Hybrid Mamba-Transformer Vision Backbone
par: Hatamizadeh, Ali, et autres
Publié: (2024)

Normalization-Equivariant Neural Networks with Application to Image Denoising
par: Herbreteau, Sébastien, et autres
Publié: (2023)

Shift-Equivariant Complex-Valued Convolutional Neural Networks
par: Gabot, Quentin, et autres
Publié: (2025)

Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance
par: Tian, Lin, et autres
Publié: (2025)

Lost in Translation: Modern Neural Networks Still Struggle With Small Realistic Image Transformations
par: Shifman, Ofir, et autres
Publié: (2024)

Building Damage Detection using Satellite Images and Patch-Based Transformer Methods
par: Siva, Smriti, et autres
Publié: (2026)

Semi-Supervised 3D Object Detection with Channel Augmentation using Transformation Equivariance
par: Kang, Minju, et autres
Publié: (2024)

REVNET: Rotation-Equivariant Point Cloud Completion via Vector Neuron Anchor Transformer
par: Ni, Zhifan, et autres
Publié: (2026)

Self-Supervised Learning Based on Transformed Image Reconstruction for Equivariance-Coherent Feature Representation
par: Wang, Qin, et autres
Publié: (2025)

Explaining Digital Pathology Models via Clustering Activations
par: Bajger, Adam, et autres
Publié: (2025)

Efficient Continuous Group Convolutions for Local SE(3) Equivariance in 3D Point Clouds
par: Weijler, Lisa, et autres
Publié: (2025)

Harmonizing knowledge Transfer in Neural Network with Unified Distillation
par: Huang, Yaomin, et autres
Publié: (2024)

Beyond Occlusion: In Search for Near Real-Time Explainability of CNN-Based Prostate Cancer Classification
par: Krebs, Martin, et autres
Publié: (2025)

When Swin Transformer Meets KANs: An Improved Transformer Architecture for Medical Image Segmentation
par: Sapkota, Nishchal, et autres
Publié: (2025)

Knowledge Distillation in Vision Transformers: A Critical Review
par: Habib, Gousia, et autres
Publié: (2023)

From Engineering Diagrams to Graphs: Digitizing P&IDs with Transformers
par: Stürmer, Jan Marius, et autres
Publié: (2024)

Local Attention Transformers for High-Detail Optical Flow Upsampling
par: Gielisse, Alexander, et autres
Publié: (2024)

Flow Equivariant Recurrent Neural Networks
par: Keller, T. Anderson
Publié: (2025)

Equivariant Image Modeling
par: Dong, Ruixiao, et autres
Publié: (2025)

E$^3$-Net: Efficient E(3)-Equivariant Normal Estimation Network
par: Wang, Hanxiao, et autres
Publié: (2024)

Flashbacks to Harmonize Stability and Plasticity in Continual Learning
par: Mahmoodi, Leila, et autres
Publié: (2025)

OVS Meets Continual Learning: Towards Sustainable Open-Vocabulary Segmentation
par: Hwang, Dongjun, et autres
Publié: (2024)

Prior-guided Hierarchical Harmonization Network for Efficient Image Dehazing
par: Su, Xiongfei, et autres
Publié: (2025)