AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Doubly-Fused ViT: Fuse Information from Vision Transformer Doubly with Local Representation

Li Gao, Dong Nie, Bo Li, Xiaofeng Ren

ECCV 2022 · Architectures and efficiency › Attention and transformers · approach: Hybrid and interpretable ViT designs · 16 citations (OpenAlex)

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 Spatial Module (SM) to Context Module (ablation)DFvT-S · ImageNet-1K val (ablation)top-1 accuracy (%): 77.0 -> 77.5Improved
add DANE fusion to CM+SM (ablation)DFvT-S · ImageNet-1K val (ablation)top-1 accuracy (%): 77.5 -> 78.3Improved
add convolutional information flow to pre-SA fusion (ablation)DFvT-S · ImageNet-1K val (ablation)top-1 accuracy (%): 72.2 -> 78.3Improved
add max-pooling information flow to pre-SA fusion (ablation)DFvT-S · ImageNet-1K val (ablation)top-1 accuracy (%): 78.1 -> 78.3Improved
replace SUM fusion by DANE (ablation)DFvT-S · ImageNet-1K val (ablation)top-1 accuracy (%): 77.5 -> 78.3Improved
replace SE fusion by DANE (ablation)DFvT-S · ImageNet-1K val (ablation)top-1 accuracy (%): 78.0 -> 78.3Improved
reverse DANE (channel and spatial attention swapped between CM and SM) (ablation)DFvT-S · ImageNet-1K val (ablation)top-1 accuracy (%): 78.3 -> 78.1Hurt
downsample input feature map before SA (Downsampled ViT vs baseline ViT) (ablation)window-SA ViT · ImageNet-1K val (design study)top-1 accuracy (%): 74.7 -> 71.9Hurt
add parallel convolution path to Downsampled ViT (ablation)Downsampled ViT · ImageNet-1K val (design study)top-1 accuracy (%): 71.9 -> 76.9Improved
use DFvT-S design instead of Parallel ViT (ablation)Parallel ViT · ImageNet-1K val (design study)throughput (imgs/s): 1843.3 -> 2203.3Improved
downsample before SA instead of baseline ViT (ablation)window-SA ViT · ImageNet-1K val (design study)throughput (imgs/s): 1168.2 -> 3091.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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