Junghun Oh
CV
Ph.D candidate
Affiliation: Department of ECE, Seoul National University (SNU), Seoul, Korea
Email: dh6dh@snu.ac.kr
Google scholar: profile
I am a Ph.D candidate student majoring in computer vision at SNU computer vision lab, advised by Prof. Kyoung Mu Lee.
Research Interests
My current research topic is representation learning, especially for generalization to unseen data distribution. More specifically, I am working on developing representation learning methods for few-shot incremental learning and out-of-distribution generalization and detection. My research topics also include network pruning and quantization for efficient neural networks and image super-resolution.
Publications
- Junghun Oh, Sungyong Baik, and Kyoung Mu Lee, “Find A Winning Sign: Sign Is All We Need to Win the Lottery”, In International Conference on Learning Representations (ICLR), 2025.
- Junghun Oh*, Sungyong Baik*, and Kyoung Mu Lee, “CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning”, In European Conference on Computer Vision (ECCV), 2024.
- Jaeha Kim, Junghun Oh, and Kyoung Mu Lee, “Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss”, In Computer Vision and Pattern Recognition (CVPR), 2024.
- Junghun Oh, Heewon Kim, Seungjun Nah, Cheeun Hong, Jonghyun Choi and Kyoung Mu Lee, “Attentive Fine-Grained Structured Sparsity for Image Restoration”, In Computer Vision and Pattern Recognition (CVPR), 2022. [PDF], [SUPP], [CODE]
- Junghun Oh, Heewon Kim, Sungyong Baik, Cheeun Hong, and Kyoung Mu Lee, “Batch Normalization Tells You Which Filter is Important”, Winter Conference on Applications of Computer Vision (WACV), 2022. [PDF], [SUPP]
- Cheeun Hong*, Heewon Kim*, Sungyong Baik, Junghun Oh, and Kyoung Mu Lee, “DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks”, Winter Conference on Applications of Computer Vision (WACV), 2022. [PDF]
- Sungyong Baik, Junghun Oh, Seokil Hong, and Kyoung Mu Lee, “Learning to Forget for Meta-Learning via Task-and-Layer-Wise Attenuation”, IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI), accepted. [PDF], [SUPP]