MVC fine-tunes Stable Diffusion with mixed CLIP caption embeddings to produce in-domain synthetic images, improving classifier accuracy on several benchmarks.
Deep generative modelling: A comparative re- view of vaes, gans, normalizing flows, energy-based and au- toregressive models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Dataset Augmentation by Mixing Visual Concepts
MVC fine-tunes Stable Diffusion with mixed CLIP caption embeddings to produce in-domain synthetic images, improving classifier accuracy on several benchmarks.