CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features

Sangdoo Yun, Dongyoon Han, Sanghyuk Chun, +3

Regional DropoutConvolutional Neural NetworkEngineeringMachine LearningImage Classification +18

CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features

Sangdoo Yun, Dongyoon Han, Seong Joon Oh, +3

arXiv (Cornell University)

Regional DropoutConvolutional Neural NetworkEngineeringMachine LearningImage Classification +18

Photorealistic Style Transfer via Wavelet Transforms

Jaejun Yoo, Youngjung Uh, Sanghyuk Chun, +2

Video RestorationImage AnalysisMachine LearningEngineeringExpressive Rendering +12

Probabilistic Embeddings for Cross-Modal Retrieval

Sanghyuk Chun, Seong Joon Oh, Rafael Sampaio de Rezende, +2

EngineeringMachine LearningCub DatasetMultimodal LearningWord Embeddings +18

Evaluating Weakly Supervised Object Localization Methods Right

Junsuk Choe, Seong Joon Oh, Seungho Lee, +3

Few-shot LearningLocalization ModelsImage AnalysisMachine LearningMachine Vision +12

Learning De-biased Representations with Biased Representations

Hyojin Bahng, Sanghyuk Chun, Sangdoo Yun, +2

arXiv (Cornell University)

Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels

Sangdoo Yun, Seong Joon Oh, Byeongho Heo, +3

Few-shot LearningMultiple Instance LearningEngineeringMachine LearningAutomatic Annotation Tool +16

Few-shot Font Generation with Localized Style Representations and Factorization

Song Park, Sanghyuk Chun, Junbum Cha, +2

Proceedings of the AAAI Conference on Artificial Intelligence

Natural Language ProcessingLocalized StylesFont StyleUniversal StylesComputational Linguistics +4

AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights

Byeongho Heo, Sanghyuk Chun, Seong Joon Oh, +5

arXiv (Cornell University)

Artificial IntelligenceNeural Scaling LawConvolutional Neural NetworkNormalization TechniquesModern Deep Learning +13

Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts

Song Park, Sanghyuk Chun, Junbum Cha, +2

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Few-shot LearningIndependence LossEngineeringMachine LearningStyle Transfer +15