Learning ordinal representations for deep reinforcement learning based object localization
US12205357B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 7, 2022 |
| Grant date | Jan 21, 2025 |
| Priority date | — |
| Expiry date | Aug 19, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/19167
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
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 allows 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.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.