CS Events
Qualifying ExamDiffusion Guided Image Generator Domain Adaptation |
|
||
Monday, March 27, 2023, 04:00pm - 06:00pm |
|||
Abstract: Classifier-free guidance can be leveraged as a critic and enable generators to distill knowledge from large-scale text-to-image diffusion models. We show that generators can be efficiently shifted into new domains indicated by text prompts without access to ground truth samples from target domains. Although not trained to minimize CLIP loss, our model achieves competitive CLIP scores and significantly lower FID than prior work on short prompts and outperforms the baseline qualitatively and quantitatively on long and complicated prompts. To our best knowledge, the proposed method is the first attempt at incorporating large-scale pre-trained diffusion models and distillation sampling for text-driven image generator domain adaptation. We further extend our work to 3D-aware style-based generators.
Speaker: Kunpeng Song
Location : CBIM 22
Committee:
Professor Ahmed Elgammal (Advisor)
Professor Dimitris Metaxas
Professor Hao Wang
Professor Mario Szegedy
Event Type: Qualifying Exam
Abstract: See above
Organization:
Rutgers University
School of Arts & Sciences
Department of Computer Science
Contact Professor Ahmed Elgammal