AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features

Sangdoo Yun, Dongyoon Han, Seong Joon Oh, Sanghyuk Chun, Junsuk Choe, Youngjoon Yoo

ICCV 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 5,740 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 CutMix augmentationResNet-50 · ImageNet-1K valtop-1 error (%): 23.68 -> 21.40Improved
add CutMix augmentationResNet-101 · ImageNet-1K valtop-1 error (%): 21.87 -> 20.17Improved
add CutMix augmentationPyramidNet-200 · CIFAR-100top-1 error (%): 16.45 -> 14.47Improved
add CutMix on top of ShakeDropPyramidNet-200 · CIFAR-100top-1 error (%): 15.08 -> 13.81Improved
apply CutMix at image level rather than feature level (ablation)PyramidNet-200 · CIFAR-100top-1 error (%): 21.80 -> 21.40Improved
sample box centers uniformly instead of Gaussian (ablation)CutMix · CIFAR-100top-1 error (%): 15.95 -> 14.47Improved
sample box size randomly instead of fixed 16x16 (ablation)CutMix · CIFAR-100top-1 error (%): 14.97 -> 14.47Improved
mix labels by area ratio instead of one-hot of larger patch (ablation)CutMix · CIFAR-100top-1 error (%): 15.89 -> 14.47Improved
mix labels by lambda instead of fixed 0.5/0.5 (ablation)CutMix · CIFAR-100top-1 error (%): 15.17 -> 14.47Improved
apply CutMix with constant probability instead of linear schedule (ablation)CutMix · CIFAR-100top-1 error (%): 14.72 -> 14.47Improved
pretrain backbone with MixupResNet-50 Faster-RCNN · Pascal VOC07 detectionmAP: 75.6 -> 73.9Hurt
pretrain backbone with CutMixResNet-50 SSD · Pascal VOC07 detectionmAP: 76.7 -> 77.6Improved

Later papers that compared with this method

12 later accepted papers report CutMix as a baseline in their results tables; 11 of them report a better number on most of the results they share with it.

4 more not listed.

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