Byeongho Heo
28 papers · 2013–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+12 more ↓ Show less ↑
π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (43) π Academic Marathon (12) π Conference Polyglot (6) π§ Keyword Pioneer
π
Conference Polyglot
(6)
π
Academic Marathon
(12)
π±
Topic Pioneer
π€
Dynamic Duo
(15)
π§¬
Topic Evolution
π
Trend Setter
β
The Questioner
π
Century Club
(28)
π
Conference Pioneer
ποΈ
Keyword Collector
(76)
β‘
Prolific Year
(6)
π₯
Unstoppable
(5)
Conferences
ICLR (7)
ECCV (6)
CVPR (5)
ICCV (5)
AAAI (4)
ICML (1)
Top co-authors
Keywords
image classification
(7)
knowledge distillation
(6)
transfer learning
(4)
model compression
(4)
vision transformer
(4)
attention mechanism
(3)
data augmentation
(3)
object detection
(3)
channel dimension
(2)
teacher network
(2)
student network
(2)
neural network
(2)
feature distillation
(2)
knowledge transfer
(1)
self-supervised learning
(1)
representation learning
(1)
model architecture
(1)
sparse representation
(1)
feature matching
(1)
multi-label classification
(1)
Papers
Masking meets Supervision: A Strong Learning Alliance
CVPR 2025
Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language Models
ICLR 2025
Morphing Tokens Draw Strong Masked Image Models
ICLR 2025
Rotary Position Embedding for Vision Transformer
ECCV 2024
Learning with Unmasked Tokens Drives Stronger Vision Learners
ECCV 2024
Similarity of Neural Architectures using Adversarial Attack Transferability
ECCV 2024
Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance
ICLR 2024
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs
ECCV 2024
SeiT++: Masked Token Modeling Improves Storage-efficient Training
ECCV 2024
Scratching Visual Transformer's Back with Uniform Attention
ICCV 2023
What Do Self-Supervised Vision Transformers Learn?
ICLR 2023
SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage
ICCV 2023
Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation
ICML 2022
Joint Global and Local Hierarchical Priors for Learned Image Compression
CVPR 2022
The Majority Can Help the Minority: Context-Rich Minority Oversampling for Long-Tailed Classification
CVPR 2022
K-Centered Patch Sampling for Efficient Video Recognition
ECCV 2022
Learning Features with Parameter-Free Layers
ICLR 2022
ViDT: An Efficient and Effective Fully Transformer-based Object Detector
ICLR 2022
Rethinking Spatial Dimensions of Vision Transformers
ICCV 2021
Re-Labeling ImageNet: From Single to Multi-Labels, From Global to Localized Labels
CVPR 2021
AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights
ICLR 2021
Rethinking Channel Dimensions for Efficient Model Design
CVPR 2021
Show, Attend and Distill: Knowledge Distillation via Attention-based Feature Matching
AAAI 2021
A Comprehensive Overhaul of Feature Distillation
ICCV 2019
Backbone Cannot Be Trained at Once: Rolling Back to Pre-Trained Network for Person Re-Identification
AAAI 2019
Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons
AAAI 2019
Knowledge Distillation with Adversarial Samples Supporting Decision Boundary
AAAI 2019
Initialization-Insensitive Visual Tracking through Voting with Salient Local Features
ICCV 2013