Learning Transferable Reward for Query Object Localization with Policy Adaptation.

Tingfeng Li Shaobo Han Martin Renqiang Min Dimitris N. Metaxas

Published in: CoRR (2022)

Keyphrases

object localization
reinforcement learning
learning algorithm
weakly supervised
data sets
learning process
prior knowledge
ground truth
relevance feedback
supervised learning
information retrieval
generative model