Open Models Almanac
Methodstraining objectiveauxiliary loss

single mention · training objective

Squared-error loss for normalized object-center coordinates

Uses squared error to train a prediction head on object-center coordinates.

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

Also called squared loss.

Filed under training objective › auxiliary loss