• Home
  • Search
  • End-to-End Visual Domain Adaptation Network for Cross-Domain 3D CPS Data Retrieval
  • Cite Icon7
  • https://doi.org/10.1109/access.2019.2937377Copy DOI Icon

End-to-End Visual Domain Adaptation Network for Cross-Domain 3D CPS Data Retrieval

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

3D CPS (Cyber Physical System) data has been widely generated and utilized for multiple applications, e.g. autonomous driving, unmanned aerial vehicle and so on. For large-scale 3D CPS data analysis, 3D object retrieval plays a significant role for urban perception. In this paper, we propose an end-to-end domain adaptation framework for cross-domain 3D objects retrieval (C3DOR-Net), which learns a joint embedding space for 3D objects from different domains in an end-to-end manner. Specifically, we focus on the unsupervised case when 3D objects in the target domain are unlabeled. To better encode a 3D object, the proposed method learns multi-view visual features in a data-driven manner for 3D object representation. Then, the domain adaptation strategy is implemented to benefit both domain alignment and final classification. Specifically, an center-based discriminative feature learning method enables the domain invariant features with better intra-class compactness and inter-class separability. C3DOR-Net can achieve remarkable retrieval performances by maximizing the inter-class divergence and minimizing the intra-class divergence. We evaluate our method on two cross-domain protocols: 1) CAD-to-CAD object retrieval on two popular 3D datasets (NTU and PSB) in three designed cross-domain scenarios; 2) SHREC’19 monocular image based 3D object retrieval. Experimental results demonstrate that our method can significantly boost the cross-domain retrieval performances.

Loading PDF

Similar Papers
  • Research Article
  • Citations88

Multiple Discrimination and Pairwise CNN for view-based 3D object retrieval

  • Feb 29, 2020
  • Neural Networks
  • Zan Gao +2
  • Supplementary Content

Parametric Procedural Models for 3D Object Retrieval, Classification and Parameterization

  • Apr 18, 2019
  • Roman Getto
  • Conference Article
  • Citations7

Consistent Domain Structure Learning and Domain Alignment for 2D Image-Based 3D Objects Retrieval

  • Jul 01, 2020
  • Yuting Su +5
  • Conference Article
  • Citations4

A novel efficient 3D object retrieval method based on representative slices

  • Sep 01, 2016
  • Ilyass Ouazzani Taybi +5
  • Conference Article
  • Citations8

View-based 3D object retrieval and recognition using tangent subspace analysis

  • Jan 27, 2008
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Fan Wang +3
  • Research Article
  • Citations13

Joint deep feature learning and unsupervised visual domain adaptation for cross-domain 3D object retrieval

  • May 14, 2020
  • Information Processing & Management
  • Wen-Hui Li +6
  • Research Article
  • Citations22

SCA-PVNet: Self-and-cross attention based aggregation of point cloud and multi-view for 3D object retrieval

  • May 11, 2024
  • Knowledge-Based Systems
  • Dongyun Lin +4
  • Research Article
  • Citations21

A motion-aware approach for efficient evaluation of continuous queries on 3D object databases

  • Apr 09, 2010
  • The VLDB Journal
  • Mohammed Eunus Ali +3
  • Research Article
  • Citations108

Multi-View Object Retrieval via Multi-Scale Topic Models.

  • Sep 27, 2016
  • IEEE Transactions on Image Processing
  • Richang Hong +4
  • Conference Article

ThOR: three-dimensional object retrieval library

  • May 02, 2015
  • Eurographics
  • Pedro B Pascoal +1
  • Research Article
  • Citations255

Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation

  • Jul 17, 2019
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Chao Chen +3
  • Research Article
  • Citations9

3D object retrieval with graph-based collaborative feature learning

  • Dec 01, 2018
  • Journal of Visual Communication and Image Representation
  • Feng Chen +2
  • Research Article
  • Citations11

Kernelized Unified Domain Adaptation on Geometrical Manifolds

  • Oct 16, 2020
  • Expert Systems with Applications
  • Rakesh Kumar Sanodiya +4
  • Research Article
  • Citations19

Variate Associated Domain Adaptation for Unsupervised Multivariate Time Series Anomaly Detection

  • Jul 26, 2024
  • ACM Transactions on Knowledge Discovery from Data
  • Yifan He +6
  • Research Article
  • Citations35

HOMDA: High-Order Moment-Based Domain Alignment for unsupervised domain adaptation

  • Dec 15, 2022
  • Knowledge-Based Systems
  • Jun Dan +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.