×

연구실

연구실 소개 및 연구분야

기계지능 및 데이터사이언스 연구실

최근 관심분야 및 주요 연구과제

- 디노이징
- 적응형 기계학습 (연속학습 및 메타학습)
- 설명가능 인공지능
- 공정한 알고리즘
- 멀티모달 데이터 비지도학습

- 뇌과학/의료영상 응용

주요 논문/특허

- Fair Feature Distillation for Visual Recognition
Donggyu Lee, Sangwon Jung, Taeeon Park, and Taesup Moon,
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021

- FBI: Fast Blind Image Denoiser for Source-Dependent Noise (Oral)
Jaeseok Byun, Sungmin Cha, and Taesup Moon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021

- CPR: Classifier-projection regularization for continual learning
Sungmin Cha, Hsiang Hsu, Taebaek Hwang, Flavio P. Calmon, and Taesup Moon
International Conference on Learning Representations (ICLR), May 2021

- GAN2GAN: Generative noise learning for blind image denoising with single noisy images
Sungmin Cha, Taeeon Park, Byeongjoon Kim, Jongduk Baek, and Taesup Moon
International Conference on Learning Representations (ICLR), May 2021

- Continual Learning with Node-Importance based Adaptive Group Sparse Regularization
Sangwon Jung, Hongjoon Ahn, Sungmin Cha, and Taesup Moon
Neural Information Processing Systems (NeurIPS), December 2020

- Learning blind pixelwise affine image denoiser with single noisy images
Jaeseok Byun and Taesup Moon
IEEE Signal Processing Letters (IF=3.268), 10.1109/LSP.2020.3002652, June 2020

- Iterative channel estimation for discrete denoising under channel uncertainty
Hongjoon Ahn and Taesup Moon
Conference on Uncertainty in Artificial Intelligence (UAI), August 2020

- Unsupervised neural universal denoiser for finite-input general-output noisy channel
Taeeon Park and Taesup Moon
International Conference on Artificial Intelligence and Statistics (AISTATS), August 2020

- Estimating PM2.5 concentration of the conterminous United States via interpretable convolutional neural networks (press)
Yongbee Park, Byungjoon Kwon, Juyeon Heo, Xuefei Hu, Yang Liu, and Taesup Moon
Environmental Pollution (IF=5.714), https://doi.org/10.1016/j.envpol.2019.113395, January 2020

- Uncertainty-based continual learning with adaptive regularization (code,press)
Hongjoon Ahn, Sungmin Cha, Donggyu Lee and Taesup Moon
Proceedings of Neural Information Processing Systems (NeurIPS), December 2019

- Fooling neural network interpretations via adversarial model manipulation (code,press)
Juyeon Heo, Sunghwan Joo, and Taesup Moon
Proceedings of Neural Information Processing Systems (NeurIPS), December 2019

- Fully convolutional pixel adaptive image denoiser (code)
Sungmin Cha and Taesup Moon
Proceedings of IEEE International Conference on Computer Vision (ICCV), October 2019

- DoPAMINE: Double-sided masked CNN for pixelwise adaptive multiplicative noise despeckling (Oral)
Sunghwan Joo, Sungmin Cha, and Taesup Moon
Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), January 2019

- Neural universal discrete denoiser
Taesup Moon, Seonwoo Min, Byunghan Lee, and Sungroh Yoon
Proceedings of Neural Information Processing Systems (NIPS), December 2016