NADA uses a vision-language class proposer plus Stable Diffusion cross-attention maps to detect objects in paintings with no bounding box supervision, reaching 45.8 AP50 weakly supervised on ArtDL 2.0 and 21.8 AP50 zero shot.
Iconographic image captioning for artworks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
No Annotations for Object Detection in Art through Stable Diffusion
NADA uses a vision-language class proposer plus Stable Diffusion cross-attention maps to detect objects in paintings with no bounding box supervision, reaching 45.8 AP50 weakly supervised on ArtDL 2.0 and 21.8 AP50 zero shot.