AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Convolutional Embedding Makes Hierarchical Vision Transformer Stronger

Cong Wang, Hongmin Xu, Xiong Zhang, Li Wang, Zhitong Zheng, Haifeng Liu

ECCV 2022 · Architectures and efficiency › Attention and transformers · approach: Hybrid and interpretable ViT designs

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add LEWin convolutional projection attention (vs shifted window attention) (ablation)CETNet-T · ImageNet-1K val (ablation, 224)top-1 accuracy (%): 82.5 -> 82.7Improved
use deep-narrow instead of shallow-wide design (ablation)CETNet-T · ImageNet-1K val (ablation, 224)top-1 accuracy (%): 82.5 -> 82.7Improved
use CE instead of Swin patch embedding and merging (ablation)CETNet shallow-wide · ImageNet-1K val (ablation, 224)top-1 accuracy (%): 81.5 -> 82.5Improved
use CE instead of CvT convolutional token embedding (ablation)CETNet shallow-wide · ImageNet-1K val (ablation, 224)top-1 accuracy (%): 82.0 -> 82.5Improved
increase CE depth from 1 to 7 MBConv layers (ablation)Swin-T · ImageNet-1K val (CE layers, Swin-T based)top-1 accuracy (%): 81.8 -> 82.6Improved
increase CE depth from 5 to 7 layers (ablation)Swin-T · ImageNet-1K val (CE layers, Swin-T based)top-1 accuracy (%): 82.4 -> 82.6No clear effect
add convolutional embedding to CvT-13 (ablation)CvT-13 · ImageNet-1K valtop-1 accuracy (%): 81.6 -> 82.1Improved
add convolutional embedding to PVT-S (ablation)PVT-S · ImageNet-1K valtop-1 accuracy (%): 79.8 -> 81.1Improved
add convolutional embedding to Swin-T (ablation)Swin-T · ImageNet-1K valtop-1 accuracy (%): 81.3 -> 82.5Improved
add convolutional embedding to CSWin-T (ablation)CSWin-T · ImageNet-1K valtop-1 accuracy (%): 82.7 -> 83.6Improved
replace Fused-MBConv with MBConv in early stage (ablation)CETNet-T · ImageNet-1K val (ablation, 224)top-1 accuracy (%): 82.7 -> 82.6No clear effect
use ResNet blocks instead of Fused-MBConv for CE (ablation)CETNet-T · ImageNet-1K val (ablation, 224)top-1 accuracy (%): 82.7 -> 82.0Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy