Online Learning via Memory: Retrieval-Augmented Detector Adaptation
Jian, Yanan, Yu, Fuxun, Zhang, Qi, Levine, William, Dubbs, Brandon, Karianakis, Nikolaos
–arXiv.org Artificial Intelligence
This paper presents a novel way of online adapting any off-the-shelf object detection model to a novel domain without retraining the detector model. Inspired by how humans quickly learn knowledge of a new subject (e.g., memorization), we allow the detector to look up similar object concepts from memory during test time. This is achieved through a retrieval augmented classification (RAC) module together with a memory bank that can be flexibly updated with new domain knowledge. We experimented with various off-the-shelf open-set detector and close-set detectors. With only a tiny memory bank (e.g., 10 images per category) and being training-free, our online learning method could significantly outperform baselines in adapting a detector to novel domains.
arXiv.org Artificial Intelligence
Sep-16-2024
- Genre:
- Research Report (0.64)
- Industry:
- Education > Educational Setting
- Online (0.63)
- Leisure & Entertainment > Sports (0.47)
- Education > Educational Setting
- Technology: