CS Events

Qualifying Exam

Diffusion Guided Image Generator Domain Adaptation

 

Download as iCal file

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