BlenDA: Domain Adaptive Object Detection through diffusion-based blending

1 code implementation • 18 Jan 2024 • Tzuhsuan Huang, Chen-Che Huang, Chung-Hao Ku, Jun-Cheng Chen

Unsupervised domain adaptation (UDA) aims to transfer a model learned using labeled data from the source domain to unlabeled data in the target domain.

Image-to-Image Translation Object +3

MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance

1 code implementation • 19 Aug 2023 • Ernie Chu, Tzuhsuan Huang, Shuo-Yen Lin, Jun-Cheng Chen

This study introduces an efficient and effective method, MeDM, that utilizes pre-trained image Diffusion Models for video-to-video translation with consistent temporal flow.