Hyeong Gwon Hong

Orcid: 0000-0003-2410-2717

According to our database1, Hyeong Gwon Hong authored at least 12 papers between 2019 and 2024.

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

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Foreseeing Reconstruction Quality of Gradient Inversion: An Optimization Perspective.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
Data Poisoning Attack Aiming the Vulnerability of Continual Learning.
Proceedings of the IEEE International Conference on Image Processing, 2023

Disposable Transfer Learning for Selective Source Task Unlearning.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Localization using Multi-Focal Spatial Attention for Masked Face Recognition.
Proceedings of the 17th IEEE International Conference on Automatic Face and Gesture Recognition, 2023

2022
Training Time Adversarial Attack Aiming the Vulnerability of Continual Learning.
CoRR, 2022

Rethinking Efficacy of Softmax for Lightweight Non-local Neural Networks.
Proceedings of the 2022 IEEE International Conference on Image Processing, 2022

Closing the Loophole: Rethinking Reconstruction Attacks in Federated Learning from a Privacy Standpoint.
Proceedings of the Annual Computer Security Applications Conference, 2022

2021
Differentiable Architecture Search Based on Coordinate Descent.
IEEE Access, 2021

De-biasing Neural Networks with Estimated Offset for Class Imbalanced Learning.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2021

2020
Continual Learning With Extended Kronecker-Factored Approximate Curvature.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Residual Continual Learning.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019
EDAS: Efficient and Differentiable Architecture Search.
CoRR, 2019


  Loading...