Past Events

Qualifying Exam

Learning Transferable Reward for Query Object Localization with Policy Adaptation


Download as iCal file

Monday, September 20, 2021, 03:00pm - 04:30pm


Speaker: Tingfeng Li

Location : Remote via Zoom


Prof. Dimitris Metaxas (advisor)

Prof. Hao Wang

Prof.Konstantinos Michmizos

Prof. Badri Nath

Event Type: Qualifying Exam

Abstract: We propose a reinforcement learning based approach to the problem of query object localization, where 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. It enables test-time policy adaptation to new environments where the reward signals are not readily available, and thus outperforms fine-tuning approaches that are limited to annotated images. In addition, the transferable reward can allow repurposing of the trained agent for new tasks, such as annotation refinement, or selective localization from multiple common objects across a set of images. Experiments on corrupted MNIST dataset and CU-Birds dataset demonstrate the effectiveness of our approach.


Meeting info: