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.

Source: CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features

Latest Papers

PAPER DATE
YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design
Yuxuan CaiHongjia LiGeng YuanWei NiuYanyu LiXulong TangBin RenYanzhi Wang
2020-09-12
Object Detection and Tracking Algorithms for Vehicle Counting: A Comparative Analysis
Vishal MandalYaw Adu-Gyamfi
2020-07-31
PP-YOLO: An Effective and Efficient Implementation of Object Detector
| Xiang LongKaipeng DengGuanzhong WangYang ZhangQingqing DangYuan GaoHui ShenJianguo RenShumin HanErrui DingShilei Wen
2020-07-23
Grad-Cam Guided Progressive Feature CutMix for Classification
Yan ZhangBinyu HeLi Sun
2020-07-17
Remix: Rebalanced Mixup
Hsin-Ping ChouShih-Chieh ChangJia-Yu PanWei WeiDa-Cheng Juan
2020-07-08
GradAug: A New Regularization Method for Deep Neural Networks
Taojiannan YangSijie ZhuChen Chen
2020-06-14
PatchUp: A Regularization Technique for Convolutional Neural Networks
| Mojtaba FaramarziMohammad AminiAkilesh BadrinaaraayananVikas VermaSarath Chandar
2020-06-14
An Empirical Analysis of the Impact of Data Augmentation on Knowledge Distillation
Deepan DasHaley MassaAbhimanyu KulkarniTheodoros Rekatsinas
2020-06-06
A U-Net Based Discriminator for Generative Adversarial Networks
Edgar Schonfeld Bernt Schiele Anna Khoreva
2020-06-01
YOLOv4: Optimal Speed and Accuracy of Object Detection
| Alexey BochkovskiyChien-Yao WangHong-Yuan Mark Liao
2020-04-23
Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification
Devesh WalawalkarZhiqiang ShenZechun LiuMarios Savvides
2020-03-29
A U-Net Based Discriminator for Generative Adversarial Networks
| Edgar SchönfeldBernt SchieleAnna Khoreva
2020-02-28
FMix: Enhancing Mixed Sample Data Augmentation
| Ethan HarrisAntonia MarcuMatthew PainterMahesan NiranjanAdam Prügel-BennettJonathon Hare
2020-02-27
On Feature Normalization and Data Augmentation
| Boyi LiFelix WuSer-Nam LimSerge BelongieKilian Q. Weinberger
2020-02-25
MaxUp: A Simple Way to Improve Generalization of Neural Network Training
Chengyue GongTongzheng RenMao YeQiang Liu
2020-02-20
Structured Consistency Loss for semi-supervised semantic segmentation
Jongmok KimJooyoung JangHyunwoo Park
2020-01-14
Semi-supervised semantic segmentation needs strong, varied perturbations
| Geoff FrenchSamuli LaineTimo AilaMichal MackiewiczGraham Finlayson
2019-06-05
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
| Sangdoo YunDongyoon HanSeong Joon OhSanghyuk ChunJunsuk ChoeYoungjoon Yoo
2019-05-13

Components

COMPONENT TYPE
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories