RODEO: Replay for Online Object Detection

08/14/2020 ∙ by Manoj Acharya, et al. ∙ 13

Humans can incrementally learn to do new visual detection tasks, which is a huge challenge for today's computer vision systems. Incrementally trained deep learning models lack backwards transfer to previously seen classes and suffer from a phenomenon known as "catastrophic forgetting." In this paper, we pioneer online streaming learning for object detection, where an agent must learn examples one at a time with severe memory and computational constraints. In object detection, a system must output all bounding boxes for an image with the correct label. Unlike earlier work, the system described in this paper can learn this task in an online manner with new classes being introduced over time. We achieve this capability by using a novel memory replay mechanism that efficiently replays entire scenes. We achieve state-of-the-art results on both the PASCAL VOC 2007 and MS COCO datasets.



There are no comments yet.


page 2

Code Repositories


Official implementation of "RODEO: Replay for Online Object Detection", BMVC 2020

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.