Sangmin Lee

Affiliations:
  • Korea Advanced Institute of Science and Technology, KAIST, Department of Mathematical Sciences, Daejeon, Korea
  • University of Ulsan College of Medicine, College of Medicine, Asan Medical Center, Seoul, Korea


According to our database1, Sangmin Lee authored at least 13 papers between 2021 and 2024.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Magnitude and angle dynamics in training single ReLU neurons.
Neural Networks, 2024

Defining Neural Network Architecture through Polytope Structures of Dataset.
CoRR, 2024

Defining Neural Network Architecture through Polytope Structures of Datasets.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Self-Supervised Debiasing Using Low Rank Regularization.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
Data Topology-Dependent Upper Bounds of Neural Network Widths.
CoRR, 2023

Training Debiased Subnetworks with Contrastive Weight Pruning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Multi-task vision transformer using low-level chest X-ray feature corpus for COVID-19 diagnosis and severity quantification.
Medical Image Anal., 2022

Efficient debiasing with contrastive weight pruning.
CoRR, 2022

AI can evolve without labels: self-evolving vision transformer for chest X-ray diagnosis through knowledge distillation.
CoRR, 2022

Support Vectors and Gradient Dynamics for Implicit Bias in ReLU Networks.
CoRR, 2022

2021
Vision Transformer using Low-level Chest X-ray Feature Corpus for COVID-19 Diagnosis and Severity Quantification.
CoRR, 2021

Severity Quantification and Lesion Localization of COVID-19 on CXR using Vision Transformer.
CoRR, 2021

Vision Transformer for COVID-19 CXR Diagnosis using Chest X-ray Feature Corpus.
CoRR, 2021


  Loading...