no code implementations • 5 Mar 2024 • Hagyeong Lee, Minkyu Kim, Jun-Hyuk Kim, Seungeon Kim, Dokwan Oh, Jaeho Lee
Recent advances in text-guided image compression have shown great potential to enhance the perceptual quality of reconstructed images.
no code implementations • 30 Aug 2023 • Yeongwoong Kim, Suyong Bahk, Seungeon Kim, Won Hee Lee, Dokwan Oh, Hui Yong Kim
We first extend an existing unidirectional NVC model to a bidirectional model, which achieves -21. 13% BD-rate gain over the unidirectional baseline model.
no code implementations • CVPR 2022 • Dasol Han, Jaewook Yoo, Dokwan Oh
In order to calculate the auxiliary loss between the feature maps of intermediate layers and the ground truth in the field of semantic segmentation, the size of each feature map must match the ground truth.
no code implementations • NeurIPS 2021 • Hee Min Choi, Hyoa Kang, Dokwan Oh
In this work, we propose a novel unsupervised learning framework for small networks that combines deep self-supervised representation learning and knowledge distillation within one-phase training.