CurveNet: Curvature-Based Multitask Learning Deep Networks for 3D Object Recognition

doi:10.1109/JAS.2020.1003324

CASIA OpenIR > 学术期刊 > IEEE/CAA Journal of Automatica Sinica

	CurveNet: Curvature-Based Multitask Learning Deep Networks for 3D Object Recognition
	A. A. M. Muzahid; Wanggen Wan; Ferdous Sohel; Lianyao Wu; Li Hou
发表期刊	IEEE/CAA Journal of Automatica Sinica
ISSN	2329-9266
	2021
卷号	8 期号:6 页码:1177-1187
摘要	In computer vision fields, 3D object recognition is one of the most important tasks for many real-world applications. Three-dimensional convolutional neural networks (CNNs) have demonstrated their advantages in 3D object recognition. In this paper, we propose to use the principal curvature directions of 3D objects (using a CAD model) to represent the geometric features as inputs for the 3D CNN. Our framework, namely CurveNet, learns perceptually relevant salient features and predicts object class labels. Curvature directions incorporate complex surface information of a 3D object, which helps our framework to produce more precise and discriminative features for object recognition. Multitask learning is inspired by sharing features between two related tasks, where we consider pose classification as an auxiliary task to enable our CurveNet to better generalize object label classification. Experimental results show that our proposed framework using curvature vectors performs better than voxels as an input for 3D object classification. We further improved the performance of CurveNet by combining two networks with both curvature direction and voxels of a 3D object as the inputs. A Cross-Stitch module was adopted to learn effective shared features across multiple representations. We evaluated our methods using three publicly available datasets and achieved competitive performance in the 3D object recognition task.
关键词	3D shape analysis convolutional neural network DNNs object classification volumetric CNN
DOI	10.1109/JAS.2020.1003324
引用统计	被引频次：34[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/44573
专题	学术期刊_IEEE/CAA Journal of Automatica Sinica
推荐引用方式 GB/T 7714	A. A. M. Muzahid,Wanggen Wan,Ferdous Sohel,et al. CurveNet: Curvature-Based Multitask Learning Deep Networks for 3D Object Recognition[J]. IEEE/CAA Journal of Automatica Sinica,2021,8(6):1177-1187.
APA	A. A. M. Muzahid,Wanggen Wan,Ferdous Sohel,Lianyao Wu,&Li Hou.(2021).CurveNet: Curvature-Based Multitask Learning Deep Networks for 3D Object Recognition.IEEE/CAA Journal of Automatica Sinica,8(6),1177-1187.
MLA	A. A. M. Muzahid,et al."CurveNet: Curvature-Based Multitask Learning Deep Networks for 3D Object Recognition".IEEE/CAA Journal of Automatica Sinica 8.6(2021):1177-1187.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
JAS-2020-0506.pdf（3792KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载