PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs.

Michael Dorkenwald Nimrod Barazani Cees G. M. Snoek Yuki M. Asano

Published in: CoRR (2024)

Keyphrases

object localisation
object detection
learned from training data
mean shift
probabilistic inference
monte carlo methods
positional information
social networks
case study
data sets