Cover Image

Flash Window Attention: speedup the attention computation for Swin Transformer

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Zhang, Zhendong
Format:	Preprint
Published:	2025
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

Enhancing DR Classification with Swin Transformer and Shifted Window Attention
by: Boulaabi, Meher, et al.
Published: (2025)

CoSwin: Convolution Enhanced Hierarchical Shifted Window Attention For Small-Scale Vision
by: Khadka, Puskal, et al.
Published: (2025)

SwinECAT: A Transformer-based fundus disease classification model with Shifted Window Attention and Efficient Channel Attention
by: Gu, Peiran, et al.
Published: (2025)

SwinShadow: Shifted Window for Ambiguous Adjacent Shadow Detection
by: Wang, Yonghui, et al.
Published: (2024)

EA-Swin: An Embedding-Agnostic Swin Transformer for AI-Generated Video Detection
by: Mai, Hung, et al.
Published: (2026)

Regional Attention-Enhanced Swin Transformer for Clinically Relevant Medical Image Captioning
by: Naz, Zubia, et al.
Published: (2025)

Classifying Deepfakes Using Swin Transformers
by: Xi, Aprille J., et al.
Published: (2025)

DarSwin: Distortion Aware Radial Swin Transformer
by: Athwale, Akshaya, et al.
Published: (2023)

Acceleration Multiple Heads Decoding for LLM via Dynamic Tree Attention
by: Zhang, Zhendong
Published: (2025)

FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention
by: Wang, Zipeng, et al.
Published: (2025)

MV-Swin-T: Mammogram Classification with Multi-view Swin Transformer
by: Sarker, Sushmita, et al.
Published: (2024)

Small Object Detection for Birds with Swin Transformer
by: Huo, Da, et al.
Published: (2025)

SparseSwin: Swin Transformer with Sparse Transformer Block
by: Pinasthika, Krisna, et al.
Published: (2023)

A New Method for Vehicle Logo Recognition Based on Swin Transformer
by: Li, Yang, et al.
Published: (2024)

SAM-Swin: SAM-Driven Dual-Swin Transformers with Adaptive Lesion Enhancement for Laryngo-Pharyngeal Tumor Detection
by: Wei, Jia, et al.
Published: (2024)

DB SwinT: A Dual-Branch Swin Transformer Network for Road Extraction in Optical Remote Sensing Imagery
by: He, Zongyang, et al.
Published: (2026)

SwinGS: Sliding Window Gaussian Splatting for Volumetric Video Streaming with Arbitrary Length
by: Liu, Bangya, et al.
Published: (2024)

Video Frame Interpolation for Polarization via Swin-Transformer
by: Huang, Feng, et al.
Published: (2024)

Lightweight Vision Transformer with Window and Spatial Attention for Food Image Classification
by: Gao, Xinle, et al.
Published: (2025)

When Swin Transformer Meets KANs: An Improved Transformer Architecture for Medical Image Segmentation
by: Sapkota, Nishchal, et al.
Published: (2025)

SwinTextUNet: Integrating CLIP-Based Text Guidance into Swin Transformer U-Nets for Medical Image Segmentation
by: Yeafi, Ashfak, et al.
Published: (2026)

CBAM-SwinT-BL: Small Rail Surface Defect Detection Method Based on Swin Transformer with Block Level CBAM Enhancement
by: Zhao, Jiayi, et al.
Published: (2024)

Brain Hematoma Marker Recognition Using Multitask Learning: SwinTransformer and Swin-Unet
by: Hirata, Kodai, et al.
Published: (2025)

SwinIFS: Landmark Guided Swin Transformer For Identity Preserving Face Super Resolution
by: Kausar, Habiba, et al.
Published: (2026)

Hybrid Swin Attention Networks for Simultaneously Low-Dose PET and CT Denoising
by: Liu, Yichao, et al.
Published: (2025)

HST-MRF: Heterogeneous Swin Transformer with Multi-Receptive Field for Medical Image Segmentation
by: Huang, Xiaofei, et al.
Published: (2023)

Representation Shift: Unifying Token Compression with FlashAttention
by: Choi, Joonmyung, et al.
Published: (2025)

Barlow-Swin: Toward a novel siamese-based segmentation architecture using Swin-Transformers
by: Haftlang, Morteza Kiani, et al.
Published: (2025)

RouteWinFormer: A Route-Window Transformer for Middle-range Attention in Image Restoration
by: Li, Qifan, et al.
Published: (2025)

DedustNet: A Frequency-dominated Swin Transformer-based Wavelet Network for Agricultural Dust Removal
by: Zhang, Shengli, et al.
Published: (2024)

Multi-Scale Representations by Varying Window Attention for Semantic Segmentation
by: Yan, Haotian, et al.
Published: (2024)

Multi-modal and Multi-view Fundus Image Fusion for Retinopathy Diagnosis via Multi-scale Cross-attention and Shifted Window Self-attention
by: Huang, Yonghao, et al.
Published: (2025)

Satellite Image Utilization for Dehazing with Swin Transformer-Hybrid U-Net and Watershed loss
by: Si, Jongwook, et al.
Published: (2025)

Cross-level Attention with Overlapped Windows for Camouflaged Object Detection
by: Li, Jiepan, et al.
Published: (2023)

Spatial-Frequency Gated Swin Transformer for Remote Sensing Single-Image Super-Resolution
by: Hossain, Md Aminur, et al.
Published: (2026)

Swin Transformer for Robust Differentiation of Real and Synthetic Images: Intra- and Inter-Dataset Analysis
by: Mehta, Preetu, et al.
Published: (2024)

nnY-Net: Swin-NeXt with Cross-Attention for 3D Medical Images Segmentation
by: Liu, Haixu, et al.
Published: (2025)

SwinLip: An Efficient Visual Speech Encoder for Lip Reading Using Swin Transformer
by: Park, Young-Hu, et al.
Published: (2025)

Underwater Image Reconstruction Using a Swin Transformer-Based Generator and PatchGAN Discriminator
by: Akash, Md. Mahbub Hasan, et al.
Published: (2025)

DualSwinFusionSeg: Multimodal Martian Landslide Segmentation via Dual Swin Transformer with Multi-Scale Fusion and UNet++
by: Kabir, Shahriar, et al.
Published: (2026)