I am currently a research resident at VinAI Research. I received my Bachelor degree in Computer Science from the Hanoi University of Science and Technology, Vietnam. Email: truongvu0911nd (at) gmail (dot) com
Create a dataset for object segmentation using pretrained text-to-image diffusion models.
Address low-quality boxes of OVOD by training a sigmoid linear classifier on pseudo labels retrieved from the top relevant region proposals to the novel text.
We propose a novel high-fidelity face swapping method called Arithmetic Face Swapping (AFS) that explicitly disentangles the intermediate latent space W+ of a pretrained StyleGAN
Propose a novel method for unsupervised image segmentation called Robust Virtual Class Contrast (RVCC), which characterizes foreground pixels based on their “virtual classes” rather than just saliency masks
