AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

VOLO: Vision Outlooker for Visual Recognition

Li Yuan, Qibin Hou, Zihang Jiang, Jiashi Feng, Shuicheng Yan

TPAMI 2022 · Architectures and efficiency › Attention and transformers · approach: Efficient and robust vision transformers · 360 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
replace 2 transformer layers with Outlookers (ablation)LV-ViT-S · ImageNet-1k valtop-1 accuracy: 83.3 -> 83.7Improved
add 2 more Outlookers (ablation)LV-ViT-S with 2 Outlookers · ImageNet-1k valtop-1 accuracy: 83.7 -> 84.0Improved
increase transformer heads from 6 to 12 (ablation)VOLO-D1 · ImageNet-1k valtop-1 accuracy: 84.0 -> 84.2Improved
raise test resolution from 224 to 384 by finetuning (ablation)VOLO-D1 · ImageNet-1k valtop-1 accuracy: 84.2 -> 85.2Improved
use Outlooker instead of local self-attention (ablation)VOLO-D1 · ImageNet-1k valtop-1 accuracy: 83.8 -> 84.2Improved
use Outlooker instead of 3x3 convolution (ablation)VOLO-D1 · ImageNet-1k valtop-1 accuracy: 83.8 -> 84.2Improved
increase Outlookers from 4 to 6 (ablation)VOLO-D1 · ImageNet-1k valtop-1 accuracy: 84.0 -> 83.9No clear effect
increase Outlooker heads from 2 to 6 (ablation)VOLO-D1 · ImageNet-1k valtop-1 accuracy: 83.9 -> 84.0Improved
increase Outlooker heads from 6 to 8 (ablation)VOLO-D1 · ImageNet-1k valtop-1 accuracy: 84.0 -> 84.0No clear effect
scale from VOLO-D1 to VOLO-D2VOLO · ImageNet-1k valtop-1 accuracy: 84.2 -> 85.2Improved
scale from VOLO-D2 to VOLO-D5VOLO · ImageNet-1k valtop-1 accuracy: 85.2 -> 86.1Improved
add Outlookers on 8x8 patch tokens (any number) over no Outlookers (ablation)LV-ViT-S · ImageNet-1k valtop-1 accuracy: 83.3 -> 84.0Improved

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