Research


AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models

NeurIPS 2025

Scheduling Weight Transitions for Quantization-Aware Training

ICCV 2025
28th Samsung Humantech Paper Award (Silver prize)

ELITE: Enhanced Language-Image Toxicity Evaluation for Safety

ICML 2025

Subnet-Aware Dynamic Supernet Training for Neural Architecture Search

CVPR 2025

Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions

AAAI 2025

Maximizing the Position Embedding for Vision Transformers with Global Average Pooling

AAAI 2025

Toward INT4 Fixed-Point Training via Exploring Quantization Error for Gradients

ECCV 2024

FYI: Flip Your Images for Dataset Distillation

ECCV 2024

AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search

CVPR 2024

Instance-Aware Group Quantization for Vision Transformers

CVPR 2024

ACLS: Adaptive and Conditional Label Smoothing for Network Calibration

ICCV 2023

RankMixup: Ranking-Based Mixup Training for Network Calibration

ICCV 2023

Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-identification

ICCV 2023

ALIFE: Adaptive Logit Regularizer and Feature Replay for Incremental Semantic Segmentation

NeurIPS 2022

Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation

NeurIPS 2022

OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search

ECCV 2022

Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation

ECCV 2022

Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation

ICCV 2021

Distance-aware Quantization

ICCV 2021

Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences

ICCV 2021

Video-based Person Re-identification with Spatial and Temporal Memory Networks

ICCV 2021

Network Quantization with Element-wise Gradient Scaling

CVPR 2021
27th Samsung Humantech Paper Award (Gold prize)

HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection

CVPR 2021

Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation

CVPR 2021

Deformable Kernel Networks for Joint Image Filtering

IJCV 2021
26th Samsung Humantech Paper Award (Silver prize)

Learning with Privileged Information for Efficient Image Super-Resolution

ECCV 2020

Learning Memory-guided Normality for Anomaly Detection

CVPR 2020

Relation Network for Person Re-identification

AAAI 2020

Learning Disentangled Representation for Robust Person Re-identification

IEEE TPAMI 2022, NeurIPS 2019

SFNet: Learning Object-aware Semantic Flow

IEEE TPAMI 2022, CVPR 2019
25th Samsung Humantech Paper Award (Silver prize)

Temporally Consistent Depth Prediction with Flow-Guided Memory Units

IEEE TITS 2019

FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence

IEEE TPAMI 2019, CVPR 2017

Proposal Flow: Semantic Correspondences from Object Proposals

IEEE TPAMI 2018, CVPR 2016

Robust Guided Image Filtering Using Nonconvex Potentials

IEEE TPAMI 2018, CVPR 2015

DASC: Robust Dense Descriptor for Multi-modal and Multi-spectral Correspondence Estimation

IEEE TPAMI 2017, CVPR 2015

SCNet: Learning Semantic Correspondence

ICCV 2017

Depth Super-Resolution by Transduction

IEEE TIP 2015

Fast Global Image Smoothing Based on Weighted Least Squares

IEEE TIP 2014
Officially integrated into OpenCV 3.1

Probability-Based Rendering for View Synthesis

IEEE TIP 2014

CONTACT

bumsub (dot) ham (at) yonsei (dot) ac (dot) kr
+82 2 2123 2768 (Office, C411)
+82 2 2123 7270 (Lab, B703)


School of Electrical and Electronic Engineering
Yonsei University, 50 Yonsei-ro, Seodaemun-Gu, Seoul, Korea