Tag

Depthwise Convolution

1 views collected around this technical thread.

Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Jul 24, 2023 · Artificial Intelligence

Understanding Slide-Transformer: An Efficient Local Attention Module for Vision Transformers

This article explains the Slide-Transformer paper, describing how the proposed Slide Attention replaces inefficient Im2Col‑based local attention with depthwise convolutions and a deformable shift module, achieving high efficiency, flexibility, and hardware‑agnostic performance for Vision Transformers.

Computer VisionDeformable ShiftDepthwise Convolution
0 likes · 13 min read
Understanding Slide-Transformer: An Efficient Local Attention Module for Vision Transformers