.png){kind=icon}
返回
Semi-supervised 3D object recognition through CNN labeling
.png){kind=icon}
OA
AI
DOI：10.1016/j.asoc.2018.02.005.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Despite the outstanding results of Convolutional Neural Networks (CNNs) in object recognition and classification, there are still some open problems to address when applying these solutions to real-world problems. Specifically, CNNs struggle to generalize under challenging scenarios, like recognizing the variability and heterogeneity of the instances of elements belonging to the same category. Some of these difficulties are directly related to the input information, 2D-based methods still show a lack of robustness against strong lighting variations, for example. In this paper, we propose to merge techniques using both 2D and 3D information to overcome these problems. Specifically, we take advantage of the spatial information in the 3D data to segment objects in the image and build an object classifier, and the classification capabilities of CNNs to semi-supervisedly label each object image for training. As the experimental results demonstrate, our model can successfully generalize for categories with high intra-class variability and outperform the accuracy of a well-known CNN model. (c) 2018 Elsevier B.V. All rights reserved.
Keyword:
Object recognition
Deep learning
Object labeling
Machine learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.6
论文数:
1.4W
被引数:
4.8W
机构
引用论文
Large-Scale Weakly Supervised Object Localization via Latent Category Learning基于潜在类别学习的大规模弱监督目标定位
PREAI
分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏Effects of the non-steroidal anti-inflammatory drug celecoxib on cholesterol containing distearoyl phosphatidylcholine membranes非甾体抗炎药塞来昔布对含胆固醇的二硬脂酰磷脂酰胆碱膜的影响.png)
SpectroscopyOAAI
SpectroscopyIF0
OAAI分享收藏 没有更多内容
没有更多内容