Presentation / Installation
CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable and Controllable Text-Guided Face Manipulation
SessionText-Guided Generation
DescriptionWe found that Contrastive Language-Image Pre-Training (CLIP) embeds texts and images in different regions in the joint space, leading to artifacts in the resulting images when optimizing toward text embeddings. Disentanglement, interpretability, and controllability are hard to guarantee. Therefore, we introduce CLIP projection-augmentation embedding (PAE) as an alternative optimization target.
Event Type
Technical Paper
TimeThursday, 10 August 20239:41am - 9:51am PDT
LocationPetree Hall D
ACM Digital Library
Technical Paper PDF
Session Time & Location
Research & Education
Livestreamed
Recorded
Artificial Intelligence/Machine Learning
Video
FC
FCS
V
VS
EFC