Bumsub Ham

papers

2,146

total citations

papers (24)

Learning Memory-Guided Normality for Anomaly Detection

CVPR 2020arXiv

811

citations

Learning by Aligning: Visible-Infrared Person Re-Identification Using Cross-Modal Correspondences

ICCV 2021arXiv

232

citations

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

CVPR 2021arXiv

120

citations

Video-Based Person Re-Identification With Spatial and Temporal Memory Networks

ICCV 2021arXiv

102

citations

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

ICCV 2021arXiv

citations

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

ICCV 2023arXiv

citations

Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation

NEURIPS 2022arXiv

citations

Distance-Aware Quantization

ICCV 2021arXiv

citations

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

NEURIPS 2022arXiv

citations

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

ECCV 2022arXiv

citations

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

CVPR 2024arXiv

citations

Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation

ECCV 2022arXiv

citations

ACLS: Adaptive and Conditional Label Smoothing for Network Calibration

ICCV 2023arXiv

citations

RankMixup: Ranking-Based Mixup Training for Network Calibration

ICCV 2023arXiv

citations

Instance-Aware Group Quantization for Vision Transformers

CVPR 2024arXiv

citations

ELITE: Enhanced Language-Image Toxicity Evaluation for Safety

ICML 2025arXiv

citations

Subnet-Aware Dynamic Supernet Training for Neural Architecture Search

CVPR 2025arXiv

citations

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

AAAI 2025arXiv

citations

Maximizing the Position Embedding for Vision Transformers with Global Average Pooling

AAAI 2025arXiv

citations

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

ECCV 2024arXiv

citations

Scheduling Weight Transitions for Quantization-Aware Training

ICCV 2025arXiv

citations

Bumsub Ham

papers (24)

Learning Memory-Guided Normality for Anomaly Detection

Learning by Aligning: Visible-Infrared Person Re-Identification Using Cross-Modal Correspondences

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

Learning with Privileged Information for Efficient Image Super-Resolution

Network Quantization With Element-Wise Gradient Scaling

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

Video-Based Person Re-Identification With Spatial and Temporal Memory Networks

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

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

Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation

Distance-Aware Quantization

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

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

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

Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation

ACLS: Adaptive and Conditional Label Smoothing for Network Calibration

RankMixup: Ranking-Based Mixup Training for Network Calibration

Instance-Aware Group Quantization for Vision Transformers

ELITE: Enhanced Language-Image Toxicity Evaluation for Safety

Subnet-Aware Dynamic Supernet Training for Neural Architecture Search

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

Maximizing the Position Embedding for Vision Transformers with Global Average Pooling

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

Scheduling Weight Transitions for Quantization-Aware Training

papers (24)

Learning Memory-Guided Normality for Anomaly Detection

Learning by Aligning: Visible-Infrared Person Re-Identification Using Cross-Modal Correspondences

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

Learning with Privileged Information for Efficient Image Super-Resolution

Network Quantization With Element-Wise Gradient Scaling

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

Video-Based Person Re-Identification With Spatial and Temporal Memory Networks

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

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

Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation

Distance-Aware Quantization

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

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

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

Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation

ACLS: Adaptive and Conditional Label Smoothing for Network Calibration

RankMixup: Ranking-Based Mixup Training for Network Calibration

Instance-Aware Group Quantization for Vision Transformers

ELITE: Enhanced Language-Image Toxicity Evaluation for Safety

Subnet-Aware Dynamic Supernet Training for Neural Architecture Search

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

Maximizing the Position Embedding for Vision Transformers with Global Average Pooling

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

Scheduling Weight Transitions for Quantization-Aware Training