arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2011.12790cs.CVcs.RO
收藏

用于机器人目标检测的快速区域建议学习

Fast Region Proposal Learning for Object Detection for Robotics

Istituto Italiano di Tecnologia(意大利理工学院);University of Genoa(热那亚大学);Massachusetts Institute of Technology(麻省理工学院)

Federico Ceola, Elisa Maiettini, Giulia Pasquale, Lorenzo Rosasco, Lorenzo Natale

摘要:

目标检测是机器人在非结构化环境中工作的一项基本任务。今天,有几种深度学习算法可以解决这个任务,并具有出色的性能。不幸的是,训练这样的系统需要几个小时的GPU时间。对于机器人来说,为了成功地适应环境的变化或学习新的物体,物体检测器可以在短时间内重新训练也很重要。最近的一种方法[1]提出了一种利用深度学习描述符的强大表示的架构,同时允许快速适应时间。利用任务在(i)区域候选生成,(ii)特征提取和(iii)区域分类中的自然分解,该方法通过仅重新训练分类层来执行检测器的快速自适应。这缩短了培训时间,同时保持了最先进的性能。在本文中,我们首先证明,通过适应,此外,在手头的任务上的区域候选生成可以获得进一步的提高精度。其次,我们用所提出的快速学习方法扩展了[1]中提出的目标检测系统,在两个不同的机器人数据集上显示了在速度和准确性方面的改进的实验证据。重现实验的代码在GitHub上公开。

英文摘要:

Object detection is a fundamental task for robots to operate in unstructured environments. Today, there are several deep learning algorithms that solve this task with remarkable performance. Unfortunately, training such systems requires several hours of GPU time. For robots, to successfully adapt to changes in the environment or learning new objects, it is also important that object detectors can be re-trained in a short amount of time. A recent method [1] proposes an architecture that leverages on the powerful representation of deep learning descriptors, while permitting fast adaptation time. Leveraging on the natural decomposition of the task in (i) regions candidate generation, (ii) feature extraction and (iii) regions classification, this method performs fast adaptation of the detector, by only re-training the classification layer. This shortens training time while maintaining state-of-the-art performance. In this paper, we firstly demonstrate that a further boost in accuracy can be obtained by adapting, in addition, the regions candidate generation on the task at hand. Secondly, we extend the object detection system presented in [1] with the proposed fast learning approach, showing experimental evidence on the improvement provided in terms of speed and accuracy on two different robotics datasets. The code to reproduce the experiments is publicly available on GitHub.

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。

↑