CutMix

CutMix is an image data augmentation strategy. Instead of simply removing pixels as in Cutout, we replace the removed regions with a patch from another image. The ground truth labels are also mixed proportionally to the number of pixels of combined images. The added patches further enhance localization ability by requiring the model to identify the object from a partial view.
相关学科: MixupSemi-Supervised Semantic SegmentationAutoAugmentCascade R-CNNCutoutAdvPropFMixMishDropBlockFine-Grained Image Recognition

学科讨论

讨论Icon

暂无讨论内容,你可以

推荐文献

按被引用数

学科管理组

暂无学科课代表,你可以申请成为课代表

重要学者

Alan L. Yuille

56169 被引用,870 篇论文

Bernt Schiele

53686 被引用,602 篇论文

Michael Jones

35461 被引用,132 篇论文

Jianfeng Gao

30435 被引用,454 篇论文

Chen Chen

23149 被引用,969 篇论文

Sanjay Singh

19371 被引用,1361 篇论文

Yun Fu

18591 被引用,525 篇论文

Lei Zhang

13050 被引用,317 篇论文
入驻作者

Wenyu Liu

12725 被引用,365 篇论文

Amit Singh

12259 被引用,761 篇论文