Open Models Almanac
Methodsmodel architecturemultimodal architecture

single mention · model architecture

Learned image-padding-status embeddings

Adds a learned embedding indicating whether an image crop has no, some, or all padding.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See multimodal architecture for the methods filed beside it.

Also called padding status.

Filed under model architecture › multimodal architecture