Boil: Towards representation change for few-shot learning J Oh*, H Yoo*, CH Kim, SY Yun ICLR, 2021, 2021 | 175 | 2021 |
Fedbabu: Towards enhanced representation for federated image classification J Oh*, S Kim*, SY Yun ICLR, 2022, 2022 | 147 | 2022 |
Comparing kullback-leibler divergence and mean squared error loss in knowledge distillation T Kim*, J Oh*, NY Kim, S Cho, SY Yun IJCAI, 2021, 2021 | 138 | 2021 |
Tornadoaggregate: Accurate and scalable federated learning via the ring-based architecture J Lee, J Oh, S Lim, SY Yun, JG Lee AAAI Workshop, 2021, 2021 | 38 | 2021 |
Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty J Oh*, S Kim*, N Ho*, JH Kim, H Song, SY Yun NeurIPS, 2022, 2022 | 25 | 2022 |
Accurate and fast federated learning via iid and communication-aware grouping J Lee, J Oh, Y Shin, JG Lee, SY Yun Arxiv, 2020 | 15 | 2020 |
ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learning J Oh*, S Kim*, N Ho*, JH Kim, H Song, SY Yun CIKM, 2022, 2022 | 8 | 2022 |
Spectrogram-channels u-net: a source separation model viewing each channel as the spectrogram of each source J Oh*, D Kim*, SY Yun Arxiv, 2018 | 7 | 2018 |
A pipelined hybrid recommender system for ranking the items on the display J Oh*, S Kim*, SY Yun, S Choi, MY Yi RecSys Workshop, 2019, 2019 | 5 | 2019 |
Interpretable Deep Learning Model for Analyzing the Relationship between the Electronic Structure and Chemisorption Property D Hong*, J Oh*, K Bang, S Kwon, SY Yun, HM Lee The Journal of Physical Chemistry Letters, 2022, 2022 | 4 | 2022 |
How to Fine-tune Models with Few Samples: Update, Data Augmentation, and Test-time Augmentation Y Kim*, J Oh*, S Kim, SY Yun ICML Workshop, 2022, 2022 | 3 | 2022 |
Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks J Oh*, J Ko*, SY Yun EMNLP, 2022, 2022 | 2 | 2022 |
SIPA: A simple framework for efficient networks G Lee*, S Bae*, J Oh, SY Yun ICDM Workshop, 2020, 2020 | 1 | 2020 |
TED talk recommender using speech transcripts J Oh*, I Lee*, Y Seonwoo*, S Sung, I Kwon, JG Lee ASONAM Demo, 2018, 2018 | 1 | 2018 |
FedFN: Feature Normalization for Alleviating Data Heterogeneity Problem in Federated Learning S Kim, G Lee, J Oh, SY Yun NeurIPS Workshop, 2023, 2023 | | 2023 |
Cross-Modal Retrieval Meets Inference: Improving Zero-Shot Classification with Cross-Modal Retrieval S Eom, N Ho, J Oh, SY Yun Arxiv, 2023 | | 2023 |
FedSOL: Stabilized Orthogonal Learning in Federated Learning G Lee, M Jeong, S Kim, J Oh, SY Yun CVPR, 2024, 2023 | | 2023 |
On the deep learning-based personalized models under source-to-source and source-to-target data heterogeneity J Oh Thesis: Korea Advanced Institute of Science and Technology (KAIST), 2023 | | 2023 |
Demystifying the Base and Novel Performances for Few-shot Class-incremental Learning J Oh, SY Yun Arxiv, 2022 | | 2022 |