Byeongho Heo

14

Papers

21

Total Citations

1

Affiliations

Affiliations

NAVER AI LAB

Papers (14)

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

Morphing Tokens Draw Strong Masked Image Models

Masking meets Supervision: A Strong Learning Alliance

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

Token Bottleneck: One Token to Remember Dynamics

A Comprehensive Overhaul of Feature Distillation

Rethinking Spatial Dimensions of Vision Transformers

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

Scratching Visual Transformer's Back with Uniform Attention

K-Centered Patch Sampling for Efficient Video Recognition

Rethinking Channel Dimensions for Efficient Model Design

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

Joint Global and Local Hierarchical Priors for Learned Image Compression

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