Imagen de Portada

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Xuwei, Li, Yang, Chen, Yudong, Liu, Jiajun, Wang, Sen
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation
por: Xu, Xuwei, et al.
Publicado: (2023)

Rethinking Vision Transformer Depth via Structural Reparameterization
por: Zhou, Chengwei, et al.
Publicado: (2025)

PaW-ViT: A Patch-based Warping Vision Transformer for Robust Ear Verification
por: Arun, Deeksha, et al.
Publicado: (2026)

ViG-LRGC: Vision Graph Neural Networks with Learnable Reparameterized Graph Construction
por: Elsharkawi, Ismael, et al.
Publicado: (2025)

ViTCN: Vision Transformer Contrastive Network For Reasoning
por: Song, Bo, et al.
Publicado: (2024)

PersonViT: Large-scale Self-supervised Vision Transformer for Person Re-Identification
por: Hu, Bin, et al.
Publicado: (2024)

ViTamin: Designing Scalable Vision Models in the Vision-Language Era
por: Chen, Jieneng, et al.
Publicado: (2024)

ReViT: Enhancing Vision Transformers Feature Diversity with Attention Residual Connections
por: Diko, Anxhelo, et al.
Publicado: (2024)

FaceLiVT: Face Recognition using Linear Vision Transformer with Structural Reparameterization For Mobile Device
por: Setyawan, Novendra, et al.
Publicado: (2025)

ViTAR: Vision Transformer with Any Resolution
por: Fan, Qihang, et al.
Publicado: (2024)

ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design
por: You, Haoran, et al.
Publicado: (2022)

ViTGaze: Gaze Following with Interaction Features in Vision Transformers
por: Song, Yuehao, et al.
Publicado: (2024)

UniViTAR: Unified Vision Transformer with Native Resolution
por: Qiao, Limeng, et al.
Publicado: (2025)

EA-ViT: Efficient Adaptation for Elastic Vision Transformer
por: Zhu, Chen, et al.
Publicado: (2025)

CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications
por: Zhang, Tianfang, et al.
Publicado: (2024)

ViT-5: Vision Transformers for The Mid-2020s
por: Wang, Feng, et al.
Publicado: (2026)

LocalViT: Analyzing Locality in Vision Transformers
por: Li, Yawei, et al.
Publicado: (2021)

FTerViT: Fully Ternary Vision Transformer
por: Ruciński, Szymon, et al.
Publicado: (2026)

Retina Vision Transformer (RetinaViT): Introducing Scaled Patches into Vision Transformers
por: Shu, Yuyang, et al.
Publicado: (2024)

Hyb-KAN ViT: Hybrid Kolmogorov-Arnold Networks Augmented Vision Transformer
por: Dey, Sainath, et al.
Publicado: (2025)

RepSFNet : A Single Fusion Network with Structural Reparameterization for Crowd Counting
por: Achmadiah, Mas Nurul, et al.
Publicado: (2026)

ViTCoP: Accelerating Large Vision-Language Models via Visual and Textual Semantic Collaborative Pruning
por: Luo, Wen, et al.
Publicado: (2026)

Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer
por: Shi, Huihong, et al.
Publicado: (2024)

ViKANformer: Embedding Kolmogorov Arnold Networks in Vision Transformers for Pattern-Based Learning
por: S, Shreyas, et al.
Publicado: (2025)

ViTOC: Vision Transformer and Object-aware Captioner
por: Huang, Feiyang
Publicado: (2024)

ACC-ViT : Atrous Convolution's Comeback in Vision Transformers
por: Ibtehaz, Nabil, et al.
Publicado: (2024)

HSViT: Horizontally Scalable Vision Transformer
por: Xu, Chenhao, et al.
Publicado: (2024)

ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding
por: Kang, Jialiang, et al.
Publicado: (2025)

FairViT: Fair Vision Transformer via Adaptive Masking
por: Tian, Bowei, et al.
Publicado: (2024)

HistoViT: Vision Transformer for Accurate and Scalable Histopathological Cancer Diagnosis
por: Ahmed, Faisal
Publicado: (2025)

ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers
por: Jiang, Yanfeng, et al.
Publicado: (2024)

ViT-AdaLA: Adapting Vision Transformers with Linear Attention
por: Li, Yifan, et al.
Publicado: (2026)

ChangeViT: Unleashing Plain Vision Transformers for Change Detection
por: Zhu, Duowang, et al.
Publicado: (2024)

IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer
por: Ma, Xiaochen, et al.
Publicado: (2023)

ViTALS: Vision Transformer for Action Localization in Surgical Nephrectomy
por: Chandra, Soumyadeep, et al.
Publicado: (2024)

ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inference
por: Hojjat, Ali, et al.
Publicado: (2025)

ConvShareViT: Enhancing Vision Transformers with Convolutional Attention Mechanisms for Free-Space Optical Accelerators
por: Ibadulla, Riad, et al.
Publicado: (2025)

Fast-COS: A Fast One-Stage Object Detector Based on Reparameterized Attention Vision Transformer for Autonomous Driving
por: Setyawan, Novendra, et al.
Publicado: (2025)

Boosting Neural Video Representation via Online Structural Reparameterization
por: Li, Ziyi, et al.
Publicado: (2025)

Feedforward 3D Editing Learns from Semantic-Part Transformation
por: Weng, Jiawei, et al.
Publicado: (2026)