Gradual adaption with memory mechanism for image-based 3D model retrieval
作者：
Highlights：
• An end-to-end unsupervised 2D image-based 3D model retrieval framework.
• Transfering knowledge from labeled 2D images to unlabeled 3D models.
• Domain-invariant features are disentangled from the original features.
• Memory module enhances domain-invariant features by representative features.
• Experiments on MI3DOR and MI3DOR-2 verified the superiority of the method.
摘要
•An end-to-end unsupervised 2D image-based 3D model retrieval framework.•Transfering knowledge from labeled 2D images to unlabeled 3D models.•Domain-invariant features are disentangled from the original features.•Memory module enhances domain-invariant features by representative features.•Experiments on MI3DOR and MI3DOR-2 verified the superiority of the method.
论文关键词：3D model retrieval,Unsupervised learning,Domain adaptation
论文评审过程：Received 11 January 2022, Revised 18 April 2022, Accepted 11 May 2022, Available online 16 May 2022, Version of Record 20 May 2022.
论文官网地址：https://doi.org/10.1016/j.imavis.2022.104482
