Image de couverture de livre

Positional Encodings Anchor Spatial Structure in Vision Transformers: A Geometric Perspective on Robustness

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Mannes, Mahmoud
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

AnchorFormer: Differentiable Anchor Attention for Efficient Vision Transformer
par: Shan, Jiquan, et autres
Publié: (2025)

Parabolic Position Encoding: Vision-Centric, Principled, Extrapolatable, General
par: Øhrstrøm, Christoffer Koo, et autres
Publié: (2026)

SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformers
par: Nikzad, Nick, et autres
Publié: (2024)

Improving Position Encoding of Transformers for Multivariate Time Series Classification
par: Foumani, Navid Mohammadi, et autres
Publié: (2023)

Rotary Position Embedding for Vision Transformer
par: Heo, Byeongho, et autres
Publié: (2024)

Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces
par: Bond, Andrew, et autres
Publié: (2026)

Revisiting Transformation Invariant Geometric Deep Learning: An Initial Representation Perspective
par: Zhang, Ziwei, et autres
Publié: (2021)

SeqPE: Transformer with Sequential Position Encoding
par: Li, Huayang, et autres
Publié: (2025)

Maximizing the Position Embedding for Vision Transformers with Global Average Pooling
par: Lee, Wonjun, et autres
Publié: (2025)

LieRE: Lie Rotational Positional Encodings
par: Ostmeier, Sophie, et autres
Publié: (2024)

Leveraging Registers in Vision Transformers for Robust Adaptation
par: Yellapragada, Srikar, et autres
Publié: (2025)

Inducing Spatial Locality in Vision Transformers through the Training Protocol
par: Toledo, Eduardo Santiago, et autres
Publié: (2026)

From Edges to Depth: Probing the Spatial Hierarchy in Vision Transformers
par: Sanghavi, Jainum
Publié: (2026)

ViTaPEs: Visuotactile Position Encodings for Cross-Modal Alignment in Multimodal Transformers
par: Lygerakis, Fotios, et autres
Publié: (2025)

Anisotropic Fourier Features for Positional Encoding in Medical Imaging
par: Jabareen, Nabil, et autres
Publié: (2025)

Approximate Nullspace Augmented Finetuning for Robust Vision Transformers
par: Liu, Haoyang, et autres
Publié: (2024)

A Geometric Perspective on Diffusion Models
par: Chen, Defang, et autres
Publié: (2023)

Mechanistic Understandings of Representation Vulnerabilities and Engineering Robust Vision Transformers
par: Islam, Chashi Mahiul, et autres
Publié: (2025)

LightMedSeg: Lightweight 3D Medical Image Segmentation with Learned Spatial Anchors
par: Tyagi, Kavyansh, et autres
Publié: (2026)

Hyperbolic Structured Classification for Robust Single Positive Multi-label Learning
par: Lin, Yiming, et autres
Publié: (2025)

Energy-Regularized Spatial Masking: A Novel Approach to Enhancing Robustness and Interpretability in Vision Models
par: Devynck, Tom, et autres
Publié: (2026)

A Language Anchor-Guided Method for Robust Noisy Domain Generalization
par: Dai, Zilin, et autres
Publié: (2025)

PEPS: Positional Encoding Projected Sampling -- Extended
par: Perez, Guillaume, et autres
Publié: (2026)

AEGIS: Anchor-Enforced Gradient Isolation for Knowledge-Preserving Vision-Language-Action Fine-Tuning
par: Singh, Guransh
Publié: (2026)

RayRoPE: Projective Ray Positional Encoding for Multi-view Attention
par: Wu, Yu, et autres
Publié: (2026)

The Effects of Grouped Structural Global Pruning of Vision Transformers on Domain Generalisation
par: Riaz, Hamza, et autres
Publié: (2025)

Language-Driven Anchors for Zero-Shot Adversarial Robustness
par: Li, Xiao, et autres
Publié: (2023)

SpecFormer: Guarding Vision Transformer Robustness via Maximum Singular Value Penalization
par: Hu, Xixu, et autres
Publié: (2024)

DPL: Decoupled Prototype Learning for Enhancing Robustness of Vision-Language Transformers to Missing Modalities
par: Lu, Jueqing, et autres
Publié: (2025)

EaqVLA: Encoding-aligned Quantization for Vision-Language-Action Models
par: Jiang, Feng, et autres
Publié: (2025)

PEVLM: Parallel Encoding for Vision-Language Models
par: Kang, Letian, et autres
Publié: (2025)

CCAR: Intrinsic Robustness as an Emergent Geometric Property
par: Samanta, Akash, et autres
Publié: (2026)

NPNet: A Non-Parametric Network with Adaptive Gaussian-Fourier Positional Encoding for 3D Classification and Segmentation
par: Saeid, Mohammad, et autres
Publié: (2026)

STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformers
par: Shao, Daqian, et autres
Publié: (2023)

PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomalies
par: Nafez, Mojtaba, et autres
Publié: (2025)

Vision-Language Models Encode Clinical Guidelines for Concept-Based Medical Reasoning
par: Harmanani, Mohamed, et autres
Publié: (2026)

On Optimal Sampling for Learning SDF Using MLPs Equipped with Positional Encoding
par: Lin, Guying, et autres
Publié: (2024)

Robustness of Structured Data Extraction from Perspectively Distorted Documents
par: Nakada, Hyakka, et autres
Publié: (2025)

VORTEX: Challenging CNNs at Texture Recognition by using Vision Transformers with Orderless and Randomized Token Encodings
par: Scabini, Leonardo, et autres
Publié: (2025)

ZACH-ViT: A Zero-Token Vision Transformer with ShuffleStrides Data Augmentation for Robust Lung Ultrasound Classification
par: Angelakis, Athanasios, et autres
Publié: (2025)