AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

SMMix: Self-Motivated Image Mixing for Vision Transformers

Mengzhao Chen, Mingbao Lin, Zhihang Lin, Yuxin Zhang, Fei Chao, Rongrong Ji

ICCV 2023 · Architectures and efficiency › Attention and transformers · approach: Token merging and masked pretraining · 14 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 CutMix with SMMixDeiT-T/S/B, CaiT, PVT, Swin-T · ImageNet-1k valtop-1 accuracy: 79.8 -> 81.1 (DeiT-S); 81.2 -> 81.8 (Swin-T)Improved
add max-min attention image mixing (ablation)DeiT-S · ImageNet-1k valtop-1 accuracy: 79.8 -> 80.4Improved
add fine-grained label assignment to max-min mixing (ablation)DeiT-S · ImageNet-1k valtop-1 accuracy: 80.4 -> 80.9Improved
add feature consistency constraint (ablation)SMMix DeiT-S · ImageNet-1k valtop-1 accuracy: 80.8 -> 81.1Improved
add TransMix or TokenMix label reconstruction to SMMix (ablation)SMMix DeiT-S · ImageNet-1k valtop-1 accuracy: 81.1 -> 81.1 (TransMix); 81.1 -> 81.2 (TokenMix)No clear effect
use pre-trained same-size DeiT-T as motivated model instead of self (ablation)SMMix DeiT-T · ImageNet-1k valtop-1 accuracy: 73.6 -> 73.5No clear effect
use larger pre-trained DeiT-S as motivated model (ablation)SMMix DeiT-T · ImageNet-1k valtop-1 accuracy: 73.6 -> 74.1Improved
vary side ratio delta (fixed 0.5, U(0,1), U(0.25,0.75)) (ablation)SMMix DeiT-S · ImageNet-1k valtop-1 accuracy: 81.0 / 81.0 / 81.1No clear effect
pretrain with SMMix instead of CutMix before transferPVT-T/S · ADE20K and COCOmIoU / box AP: 41.9 -> 43.0 mIoU (PVT-S); 40.4 -> 41.0 AP (PVT-S)Improved
train with SMMix instead of CutMixDeiT-S · ImageNet-Atop-1 accuracy: 18.7 -> 22.0Improved
use SMMix instead of CutMixmixed image quality · ImageNet-1k mixed imagestop-2 accuracy of mixed images: 23.8% -> 48.3%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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