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 1802.06964cs.CV
收藏

基于共生矩阵分析的半监督训练目标检测

Co-occurrence matrix analysis-based semi-supervised training for object detection

DGIST(韩国大邱庆北科学技术院);KAIST(韩国科学技术院);SK Telecom(SK电讯)

Min-Kook Choi, Jaehyeong Park, Jihun Jung, Heechul Jung, Jin-Hee Lee, Woong Jae Won, Woo Young Jung, Jincheol Kim, Soon Kwon

摘要:

使用卷积神经网络(CNN)训练对象识别网络的最重要因素之一是提供伴随人类判断的注释数据。特别地,在目标检测或语义分割中,注释过程需要相当多的人力。在本文中,我们提出了一种基于半监督学习(SSL)的训练方法用于目标检测,该方法通过应用先前从注释数据集训练的网络来自动标记未注释的数据。由于经过训练的网络的推断标签取决于学习的参数,因此重新训练网络通常是没有意义的。为了将有价值的推断标签转移到未标记的数据,我们提出了一种基于共生矩阵分析的重新对齐方法,该方法考虑了估计标签的单热矢量编码和图像中对象之间的相关性。我们使用MS-COCO检测数据集来验证所提出的SSL方法和可变形神经网络(D-ConvNets)作为基本训练的对象检测器的性能。现有的最先进的检测器(DConvNets,YOLO v2,和Single Shot multi-box detector(SSD))的性能可以通过所提出的SSL方法来提高,而无需使用额外的模型参数或修改网络架构。

英文摘要:

One of the most important factors in training object recognition networks using convolutional neural networks (CNNs) is the provision of annotated data accompanying human judgment. Particularly, in object detection or semantic segmentation, the annotation process requires considerable human effort. In this paper, we propose a semi-supervised learning (SSL)-based training methodology for object detection, which makes use of automatic labeling of un-annotated data by applying a network previously trained from an annotated dataset. Because an inferred label by the trained network is dependent on the learned parameters, it is often meaningless for re-training the network. To transfer a valuable inferred label to the unlabeled data, we propose a re-alignment method based on co-occurrence matrix analysis that takes into account one-hot-vector encoding of the estimated label and the correlation between the objects in the image. We used an MS-COCO detection dataset to verify the performance of the proposed SSL method and deformable neural networks (D-ConvNets) as an object detector for basic training. The performance of the existing state-of-the-art detectors (DConvNets, YOLO v2, and single shot multi-box detector (SSD)) can be improved by the proposed SSL method without using the additional model parameter or modifying the network architecture.

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。

↑