Kwanghoon Sohn* — accepted AI-conference papers

2024

EBDM: Exemplar-guided Image Translation with Brownian-bridge Diffusion Models

Eungbean Lee, Somi Jeong, Kwanghoon Sohn*

ECCV 2024poster

"Exemplar-guided image translation, synthesizing photo-realistic images that conform to both structural control and style exemplars, is attracting attention due to its ability to enhance user control over style manipulation. Previous methodologies have predominantly depended on establishing dense co…

Cited by 2 Source ↗PDF ↗Scholar ↗

2024

Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation

Ilhoon Yoon, Hyeongjun Kwon, Jin Kim, Junyoung Park, Hyunsung Jang, Kwanghoon Sohn*

ECCV 2024poster

"Source-Free domain adaptive Object Detection (SFOD) is a promising strategy for deploying trained detectors to new, unlabeled domains without accessing source data, addressing significant concerns around data privacy and efficiency. Most SFOD methods leverage a Mean-Teacher (MT) self-training parad…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗