Picture for Junghyup Lee

Junghyup Lee

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

Add code
Jul 17, 2024
Viaarxiv icon

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

Add code
Mar 28, 2024
Viaarxiv icon

RankMixup: Ranking-Based Mixup Training for Network Calibration

Add code
Aug 23, 2023
Viaarxiv icon

Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation

Add code
Oct 12, 2022
Figure 1 for Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation
Figure 2 for Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation
Figure 3 for Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation
Figure 4 for Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation
Viaarxiv icon

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

Add code
Jul 21, 2022
Figure 1 for OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search
Figure 2 for OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search
Figure 3 for OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search
Figure 4 for OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search
Viaarxiv icon

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

Add code
Aug 20, 2021
Figure 1 for Video-based Person Re-identification with Spatial and Temporal Memory Networks
Figure 2 for Video-based Person Re-identification with Spatial and Temporal Memory Networks
Figure 3 for Video-based Person Re-identification with Spatial and Temporal Memory Networks
Figure 4 for Video-based Person Re-identification with Spatial and Temporal Memory Networks
Viaarxiv icon

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

Add code
Aug 17, 2021
Figure 1 for Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences
Figure 2 for Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences
Figure 3 for Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences
Figure 4 for Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences
Viaarxiv icon

Distance-aware Quantization

Add code
Aug 16, 2021
Figure 1 for Distance-aware Quantization
Figure 2 for Distance-aware Quantization
Figure 3 for Distance-aware Quantization
Figure 4 for Distance-aware Quantization
Viaarxiv icon

Network Quantization with Element-wise Gradient Scaling

Add code
Apr 02, 2021
Figure 1 for Network Quantization with Element-wise Gradient Scaling
Figure 2 for Network Quantization with Element-wise Gradient Scaling
Figure 3 for Network Quantization with Element-wise Gradient Scaling
Figure 4 for Network Quantization with Element-wise Gradient Scaling
Viaarxiv icon

Learning with Privileged Information for Efficient Image Super-Resolution

Add code
Jul 15, 2020
Figure 1 for Learning with Privileged Information for Efficient Image Super-Resolution
Figure 2 for Learning with Privileged Information for Efficient Image Super-Resolution
Figure 3 for Learning with Privileged Information for Efficient Image Super-Resolution
Figure 4 for Learning with Privileged Information for Efficient Image Super-Resolution
Viaarxiv icon