Donghyeon Baek
8 papers · 2021–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (14) π Academic Marathon (5) π Conference Polyglot (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (14)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π₯
Unstoppable
(6)
Conferences
ECCV (2)
ICCV (2)
NIPS (2)
CVPR (1)
WACV (1)
Top co-authors
Keywords
semantic segmentation
(3)
supernet training
(2)
neural architecture search
(2)
vision transformer
(1)
knowledge distillation
(1)
incremental learning
(1)
class-incremental learning
(1)
label smoothing
(1)
network optimization
(1)
memory efficiency
(1)
loss function
(1)
progressive training
(1)
feature extractor
(1)
model efficiency
(1)
learning rate scheduler
(1)
joint embedding
(1)
network calibration
(1)
semantic prototype
(1)
forgetting problem
(1)
dynamic training strategy
(1)
Papers
GrowTAS: Progressive Expansion from Small to Large Subnets for Efficient ViT Architecture Search
WACV 2026
Subnet-Aware Dynamic Supernet Training for Neural Architecture Search
CVPR 2025
FYI: Flip Your Images for Dataset Distillation
ECCV 2024
ACLS: Adaptive and Conditional Label Smoothing for Network Calibration
ICCV 2023
OIMNet++: Prototypical Normalization and Localization-Aware Learning for Person Search
ECCV 2022
Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation
NIPS 2022
ALIFE: Adaptive Logit Regularizer and Feature Replay for Incremental Semantic Segmentation
NIPS 2022
Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation
ICCV 2021