AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data

Shaoli Huang, Xinchao Wang, Dacheng Tao

AAAI 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 114 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
Use semantic-ratio label weights instead of area-ratio label weights (ablation)SnapMix image mixing on fine-grained recognition · CUB, Cars, and Aircrafttop-1 accuracyImproved
Use asymmetric rather than symmetric image mixing (ablation)SnapMix · CUB, Cars, and Aircrafttop-1 accuracyImproved
Set alpha to 5.0 rather than other tested values (ablation)SnapMix on ResNet-50 · CUBaccuracy: 87.22, 87.23, 87.25, 87.30, 87.75, 87.30, 87.54Improved
Apply SnapMix rather than the strongest listed mixing augmentationResNet-18 and ResNet-34 · CUB, Cars, and Aircrafttop-1 accuracyImproved
Apply SnapMix rather than the strongest listed mixing augmentationResNet-50 and ResNet-101 · CUB, Cars, and Aircrafttop-1 accuracyImproved
Apply CutMix rather than the baselineResNet-18 · CUBtop-1 accuracy: 82.35 -> 80.16Hurt
Apply CutOut rather than the baselineResNet-18 · CUBtop-1 accuracy: 82.35 -> 80.54Hurt
Apply SnapMix rather than the baselineResNet-18 · CUB, training from scratchaccuracy: 64.98 -> 70.31Improved
Apply SnapMix rather than MixUpResNet-50 · CUB, training from scratchaccuracy: 72.39 -> 72.17Hurt
Apply SnapMix rather than the baselineInceptionV3 and DenseNet121 · CUBaccuracyImproved

Later papers that compared with this method

1 later accepted paper reports SnapMix as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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