RODEO: Replay for Online Object Detection
This addresses the challenge of incremental learning in computer vision systems, enabling them to learn new object detection tasks online without forgetting previous ones.
The paper tackles the problem of catastrophic forgetting in online streaming learning for object detection, achieving state-of-the-art results on PASCAL VOC 2007 and MS COCO datasets.
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.