论文标题
牛仔竞技表演：在线对象检测重播
RODEO: Replay for Online Object Detection
论文作者
论文摘要
人类可以逐步学习执行新的视觉检测任务，这对于当今的计算机视觉系统来说是一个巨大的挑战。经过逐步训练的深度学习模型缺乏向后转移到先前看到的课程的转移，并且遭受了一种被称为$“灾难性遗忘的现象。” $在本文中，我们先驱在线流媒体流学习以进行对象检测，在这种情况下，代理商必须在一个严重的记忆和计算约束中学习一个例子。在对象检测中，系统必须输出具有正确标签的图像的所有边界框。与较早的工作不同，本文中描述的系统可以在线学习此任务，随着时间的流逝，新课程将引入。我们通过使用新型的记忆重播机制来实现此功能，该机制有效地重播整个场景。我们在Pascal VOC 2007和MS Coco数据集上获得最新的结果。
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.
