End-to-end masked-image VAE plus normalizing flow yields FID 2.50 on ImageNet 256 with 128 tokens and higher linear-probe accuracy than unmasked counterparts.
In: arXiv preprint arXiv:2405.15438 (2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation
End-to-end masked-image VAE plus normalizing flow yields FID 2.50 on ImageNet 256 with 128 tokens and higher linear-probe accuracy than unmasked counterparts.