Learning Transferable Reward for Query Object Localization with Policy Adaptation

Abstract

We propose a reinforcement learning based approach to query object localization, for which an agent is trained to localize objects of interest specified by a small exemplary set. We learn a transferable reward signal formulated using the exemplary set by ordinal metric learning. Our proposed method enables test-time policy adaptation to new environments where the reward signals are not readily available, and outperforms fine-tuning approaches that are limited to annotated images. In addition, the transferable reward allows repurposing the trained agent from one specific class to another class. Experiments on corrupted MNIST, CU-Birds, and COCO datasets demonstrate the effectiveness of our approach.

Cite

Text

Li et al. "Learning Transferable Reward for Query Object Localization with Policy Adaptation." International Conference on Learning Representations, 2022.

Markdown

[Li et al. "Learning Transferable Reward for Query Object Localization with Policy Adaptation." International Conference on Learning Representations, 2022.](https://mlanthology.org/iclr/2022/li2022iclr-learning/)

BibTeX

@inproceedings{li2022iclr-learning,
  title     = {{Learning Transferable Reward for Query Object Localization with Policy Adaptation}},
  author    = {Li, Tingfeng and Han, Shaobo and Min, Martin Renqiang and Metaxas, Dimitris N.},
  booktitle = {International Conference on Learning Representations},
  year      = {2022},
  url       = {https://mlanthology.org/iclr/2022/li2022iclr-learning/}
}