Cover Image

UniForm: A Reuse Attention Mechanism Optimized for Efficient Vision Transformers on Edge Devices

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yeom, Seul-Ki, Kim, Tae-Ho
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Video Self-Distillation for Single-Image Encoders: A Step Toward Physically Plausible Perception
by: Simon, Marcel, et al.
Published: (2025)

VINO: Video-driven Invariance for Non-contextual Objects via Structural Prior Guided De-contextualization
by: Yeom, Seul-Ki, et al.
Published: (2026)

UniFormer: Unifying Convolution and Self-attention for Visual Recognition
by: Li, Kunchang, et al.
Published: (2022)

UniForm: A Unified Multi-Task Diffusion Transformer for Audio-Video Generation
by: Zhao, Lei, et al.
Published: (2025)

MicroViT: A Vision Transformer with Low Complexity Self Attention for Edge Device
by: Setyawan, Novendra, et al.
Published: (2025)

Factorized Multi-Resolution HashGrid for Efficient Neural Radiance Fields: Execution on Edge-Devices
by: Jun-Seong, Kim, et al.
Published: (2026)

Cooperative Inference for Real-Time 3D Human Pose Estimation in Multi-Device Edge Networks
by: Choi, Hyun-Ho, et al.
Published: (2025)

Efficient Partitioning Vision Transformer on Edge Devices for Distributed Inference
by: Liu, Xiang, et al.
Published: (2024)

Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers
by: Lee, Sanghyeok, et al.
Published: (2024)

ToFe: Lagged Token Freezing and Reusing for Efficient Vision Transformer Inference
by: Zhang, Haoyue, et al.
Published: (2025)

Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features
by: Lee, Jewon, et al.
Published: (2025)

EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devices
by: Saha, Shaibal, et al.
Published: (2025)

EdgeFusion: On-Device Text-to-Image Generation
by: Castells, Thibault, et al.
Published: (2024)

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

ToSA: Token Selective Attention for Efficient Vision Transformers
by: Singh, Manish Kumar, et al.
Published: (2024)

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers
by: Lu, Andrew, et al.
Published: (2025)

S2AFormer: Strip Self-Attention for Efficient Vision Transformer
by: Xu, Guoan, et al.
Published: (2025)

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer
by: Letourneau, Pierre-David, et al.
Published: (2024)

ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models
by: Lee, Jewon, et al.
Published: (2025)

SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices
by: Hu, Dongting, et al.
Published: (2026)

DuoFormer: Leveraging Hierarchical Representations by Local and Global Attention Vision Transformer
by: Tang, Xiaoya, et al.
Published: (2025)

Representative Attention For Vision Transformers
by: Li, Yuntong, et al.
Published: (2026)

Vision Transformers with Hierarchical Attention
by: Liu, Yun, et al.
Published: (2021)

NuWa: Deriving Lightweight Task-Specific Vision Transformers for Edge Devices
by: Wei, Ziteng, et al.
Published: (2025)

Reusing Attention for One-stage Lane Topology Understanding
by: Li, Yang, et al.
Published: (2025)

xEdgeFace: Efficient Cross-Spectral Face Recognition for Edge Devices
by: George, Anjith, et al.
Published: (2025)

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers
by: Hong, Jung-Ho, et al.
Published: (2025)

ROI-Aware Multiscale Cross-Attention Vision Transformer for Pest Image Identification
by: Kim, Ga-Eun, et al.
Published: (2023)

UniMoD: Efficient Unified Multimodal Transformers with Mixture-of-Depths
by: Mao, Weijia, et al.
Published: (2025)

EdgeFM: Efficient Edge Inference for Vision-Language Models
by: Deng, Mengling, et al.
Published: (2026)

Structured Initialization for Attention in Vision Transformers
by: Zheng, Jianqiao, et al.
Published: (2024)

Vision Transformers are Circulant Attention Learners
by: Han, Dongchen, et al.
Published: (2025)

Multi-manifold Attention for Vision Transformers
by: Konstantinidis, Dimitrios, et al.
Published: (2022)

HAViT: Historical Attention Vision Transformer
by: Banik, Swarnendu, et al.
Published: (2026)

EViT-Unet: U-Net Like Efficient Vision Transformer for Medical Image Segmentation on Mobile and Edge Devices
by: Li, Xin, et al.
Published: (2024)

EcoLens: Leveraging Multi-Objective Bayesian Optimization for Energy-Efficient Video Processing on Edge Devices
by: Civjan, Benjamin, et al.
Published: (2025)

EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation
by: Kodavanti, Sravanth, et al.
Published: (2026)

Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Sets
by: Decatur, Dale, et al.
Published: (2025)

HEART-VIT: Hessian-Guided Efficient Dynamic Attention and Token Pruning in Vision Transformer
by: Uddin, Mohammad Helal, et al.
Published: (2025)

TCSAFormer: Efficient Vision Transformer with Token Compression and Sparse Attention for Medical Image Segmentation
by: Xia, Zunhui, et al.
Published: (2025)