arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2103.02603cs.CVcs.AIcs.LG
收藏

面向开放世界的目标检测

Towards Open World Object Detection

Indian Institute of Technology Hyderabad(印度理工学院海得拉巴分校);Mohamed bin Zayed University of AI(穆罕默德·本·扎耶德人工智能大学);Australian National University(澳大利亚国立大学);Linköping University(林雪平大学)

K J Joseph, Salman Khan, Fahad Shahbaz Khan, Vineeth N Balasubramanian

摘要:

人类有一种自然的本能来识别环境中的未知对象实例。当相应的知识最终可用时,对这些未知实例的内在好奇心有助于了解它们。这促使我们提出了一个新的计算机视觉问题,称为:“开放世界目标检测”,其中模型的任务是:1)将尚未引入的对象识别为“未知”,而无需明确的监督,以及2)当相应的标签逐渐接收时,逐渐学习这些识别的未知类别,而不会忘记以前学习的类别。我们制定的问题,介绍了一个强大的评估协议,并提供了一种新的解决方案,我们称之为ORE:开放世界对象检测器,基于对比聚类和基于能量的未知识别。我们的实验评估和消融研究分析了ORE在实现开放世界目标方面的疗效。作为一个有趣的副产品,我们发现,识别和表征未知的情况下,有助于减少混乱的增量目标检测设置,在那里我们实现了最先进的性能,没有额外的方法的努力。我们希望我们的工作将吸引进一步的研究到这个新确定的,但关键的研究方向。

英文摘要:

Humans have a natural instinct to identify unknown object instances in their environments. The intrinsic curiosity about these unknown instances aids in learning about them, when the corresponding knowledge is eventually available. This motivates us to propose a novel computer vision problem called: `Open World Object Detection', where a model is tasked to: 1) identify objects that have not been introduced to it as `unknown', without explicit supervision to do so, and 2) incrementally learn these identified unknown categories without forgetting previously learned classes, when the corresponding labels are progressively received. We formulate the problem, introduce a strong evaluation protocol and provide a novel solution, which we call ORE: Open World Object Detector, based on contrastive clustering and energy based unknown identification. Our experimental evaluation and ablation studies analyze the efficacy of ORE in achieving Open World objectives. As an interesting by-product, we find that identifying and characterizing unknown instances helps to reduce confusion in an incremental object detection setting, where we achieve state-of-the-art performance, with no extra methodological effort. We hope that our work will attract further research into this newly identified, yet crucial research direction.

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。

↑