• Home
  • Search
  • Dual-level Embedding Alignment Network for 2D Image-Based 3D Object Retrieval
  • Cite Icon46
  • https://doi.org/10.1145/3343031.3351011Copy DOI Icon

Dual-level Embedding Alignment Network for 2D Image-Based 3D Object Retrieval

  • Oct 15, 2019
  • Heyu Zhou +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Recent advances in 3D modeling software and 3D capture devices contribute to the availability of large-scale 3D objects. However, manually labelled large-scale 3D object dataset is still too expensive to build in practice. An intuitive idea is to transfer the knowledge from label-rich 2D images (source domain) to unlabelled 3D objects (target domain) to facilitate 3D big data management. In this paper, we propose an unsupervised dual-level embedding alignment (DLEA) network for a new task, 2D image-based 3D object retrieval. It mainly consists of two modules, visual feature learning and cross-domain feature adaptation, for jointly optimizing. The first module transforms individual 3D object into a set of multi-view images and utilizes 2D CNNs to extract visual features of both multi-view image sets and the source 2D images. For multi-view fusion by reducing the distribution divergence between both domains, we propose a cross-domain view-wise attention mechanism to adaptively compute the weights of individual views and aggregate them into a compact descriptor to narrow the gap between source and target domains. With the visual representation of both domains, the module of cross-domain feature adaptation aims to enforce the domain-level and class-level embedding alignment of cross-domain feature spaces. For domain-level embedding alignment, we train a discriminator to align the global distribution statistics of both spaces. For class-level embedding alignment, we map the features in the same class but from different domains nearby through aligning the centroid of each class from both domains. To our knowledge, this is the first unsupervised work to jointly realize cross-domain feature learning and distribution alignment in an end-to-end manner for this new task. Moreover, we constructed two new datasets, MI3DOR and MI3DOR-2, to advocate the research on this topic. Extensive comparison experiments can demonstrate the superiority of DLEA against the state-of-art methods.

Similar Papers
  • Research Article
  • Citations96

VDM-DA: Virtual Domain Modeling for Source Data-Free Domain Adaptation

  • Jun 01, 2022
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Jiayi Tian +3
  • PDF
  • Research Article

Learning Transferable Convolutional Proxy by SMI-Based Matching Technique

  • Oct 14, 2020
  • Shock and Vibration
  • Wei Jin +1
  • Research Article
  • Citations52

Deep Asymmetric Transfer Network for Unbalanced Domain Adaptation

  • Apr 25, 2018
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Daixin Wang +2
  • Book Chapter
  • Citations2

Cross-Domain Matrix Factorization for Multiple Implicit-Feedback Domains

  • Jan 01, 2015
  • Rohit Parimi +1
  • Research Article
  • Citations83

Knowledge-leveraged transfer fuzzy C-Means for texture image segmentation with self-adaptive cluster prototype matching

  • May 19, 2017
  • Knowledge-Based Systems
  • Pengjiang Qian +6
  • Research Article
  • Citations157

Heterogeneous Domain Adaptation: An Unsupervised Approach.

  • Nov 30, 2020
  • IEEE Transactions on Neural Networks and Learning Systems
  • Feng Liu +2
  • Research Article
  • Citations35

Prototype-Based Multisource Domain Adaptation.

  • Oct 01, 2022
  • IEEE Transactions on Neural Networks and Learning Systems
  • Lihua Zhou +4
  • Research Article

SAFENet: Semantic-Aware Feature Enhancement Network for unsupervised cross-domain road scene segmentation

  • Nov 04, 2024
  • Image and Vision Computing
  • Dexin Ren +4
  • Research Article
  • Citations10

Multi-source transfer regression via source-target pairwise segment

  • Nov 06, 2020
  • Information Sciences
  • Kai Yang +3
  • Research Article
  • Citations4

Enhancing Cross-Domain Remote Sensing Scene Classification by Multi-Source Subdomain Distribution Alignment Network

  • Apr 05, 2025
  • Remote Sensing
  • Yong Wang +6
  • Research Article
  • Citations6

AdaTreeFormer: Few shot domain adaptation for tree counting from a single high-resolution image

  • Jun 25, 2024
  • ISPRS Journal of Photogrammetry and Remote Sensing
  • Hamed Amini Amirkolaee +3
  • Research Article
  • Citations40

Physically Constrained Transfer Learning Through Shared Abundance Space for Hyperspectral Image Classification

  • Aug 21, 2020
  • IEEE Transactions on Geoscience and Remote Sensing
  • Ying Qu +5
  • Research Article
  • Citations4

Bi-adapting kernel learning for unsupervised domain adaptation

  • Jul 27, 2019
  • Neurocomputing
  • Zengmao Wang +4
  • Research Article
  • Citations7

Unsupervised Domain Expansion for Visual Categorization

  • Nov 12, 2021
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Jie Wang +4
  • Research Article
  • Citations37

Fault Diagnosis of Delta 3D Printers Using Transfer Support Vector Machine With Attitude Signals

  • Jan 01, 2019
  • IEEE Access
  • Jianwen Guo +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.