Byeongho Heo

Affiliations

NAVER AI LAB

papers

1,398

total citations

papers (15)

Rethinking Spatial Dimensions of Vision Transformers

ICCV 2021arXiv

700

citations

The Majority Can Help the Minority: Context-Rich Minority Oversampling for Long-Tailed Classification

CVPR 2022arXiv

207

citations

Re-Labeling ImageNet: From Single to Multi-Labels, From Global to Localized Labels

CVPR 2021arXiv

164

citations

Byeongho Heo

Affiliations

papers (15)

Rethinking Spatial Dimensions of Vision Transformers

The Majority Can Help the Minority: Context-Rich Minority Oversampling for Long-Tailed Classification

Re-Labeling ImageNet: From Single to Multi-Labels, From Global to Localized Labels

Rethinking Channel Dimensions for Efficient Model Design

Joint Global and Local Hierarchical Priors for Learned Image Compression

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs

Scratching Visual Transformer's Back with Uniform Attention

Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance

SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage

Learning with Unmasked Tokens Drives Stronger Vision Learners

Masking meets Supervision: A Strong Learning Alliance

Morphing Tokens Draw Strong Masked Image Models

SeiT++: Masked Token Modeling Improves Storage-efficient Training

Token Bottleneck: One Token to Remember Dynamics

K-Centered Patch Sampling for Efficient Video Recognition

papers (15)

Rethinking Spatial Dimensions of Vision Transformers

The Majority Can Help the Minority: Context-Rich Minority Oversampling for Long-Tailed Classification

Re-Labeling ImageNet: From Single to Multi-Labels, From Global to Localized Labels

Rethinking Channel Dimensions for Efficient Model Design

Joint Global and Local Hierarchical Priors for Learned Image Compression

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs

Scratching Visual Transformer's Back with Uniform Attention

Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance

SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage

Learning with Unmasked Tokens Drives Stronger Vision Learners

Masking meets Supervision: A Strong Learning Alliance

Morphing Tokens Draw Strong Masked Image Models

SeiT++: Masked Token Modeling Improves Storage-efficient Training

Token Bottleneck: One Token to Remember Dynamics

K-Centered Patch Sampling for Efficient Video Recognition