arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.08242cs.CVcs.AI
收藏

AI在线滤波器用于真实世界图像识别

AI Online Filters to Real World Image Recognition

Stanford University(斯坦福大学);Sunnyvale, USA(美国桑尼维尔(Sunnyvale, USA))

Hai Xiao, Jin Shang, Mengyuan Huang

摘要:

用标记数据集训练的深度人工神经网络广泛用于当今的许多视觉和机器人应用中。在人工智能方面,这些被称为反射模型,指的是它们不会自我进化或主动适应环境变化的事实。随着对智能机器人控制的需求扩展到许多高级任务,强化学习和基于状态的模型发挥着越来越重要的作用。在此,在计算机视觉和机器人领域,我们研究了一种新的方法来增加强化控制到图像识别反射模型,以获得更好的整体性能,特别是更广泛的环境范围超出了预期的任务反射模型。遵循一个共同的基础设施与环境传感和基于AI的建模自适应代理,我们实现了多种类型的AI控制代理。最后,我们提供了这些代理与基线的比较结果,并深入分析了它们的好处,以提高在现实世界中的整体图像识别性能。

英文摘要:

Deep artificial neural networks, trained with labeled data sets are widely used in numerous vision and robotics applications today. In terms of AI, these are called reflex models, referring to the fact that they do not self-evolve or actively adapt to environmental changes. As demand for intelligent robot control expands to many high level tasks, reinforcement learning and state based models play an increasingly important role. Herein, in computer vision and robotics domain, we study a novel approach to add reinforcement controls onto the image recognition reflex models to attain better overall performance, specifically to a wider environment range beyond what is expected of the task reflex models. Follow a common infrastructure with environment sensing and AI based modeling of self-adaptive agents, we implement multiple types of AI control agents. To the end, we provide comparative results of these agents with baseline, and an insightful analysis of their benefit to improve overall image recognition performance in real world.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑