Dae-hwan Kim — accepted AI-conference papers

2024

Textual Query-Driven Mask Transformer for Domain Generalized Segmentation

Byeonghyun Pak, Byeongju Woo, Sunghwan Kim, Dae-hwan Kim, Hoseong Kim*

ECCV 2024poster

"In this paper, we introduce a method to tackle Domain Generalized Semantic Segmentation (DGSS) by utilizing domain-invariant semantic knowledge from text embeddings of vision-language models. We employ the text embeddings as object queries within a transformer-based segmentation framework (textual…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗

2023

Texture Learning Domain Randomization for Domain Generalized Segmentation

Sunghwan Kim, Dae-hwan Kim, Hoseong Kim

ICCV 2023poster

Deep Neural Networks (DNNs)-based semantic segmentation models trained on a source domain often struggle to generalize to unseen target domains, i.e., a domain gap problem. Texture often contributes to the domain gap, making DNNs vulnerable to domain shift because they are prone to be texture-biased…

Cited by 25 PDF ↗code ↗Scholar ↗