4.7 Article

Self-Supervised Auxiliary Domain Alignment for Unsupervised 2D Image-Based 3D Shape Retrieval

Journal

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2022.3191761

Keywords

Shape; Three-dimensional displays; Task analysis; Representation learning; Semantics; Feature extraction; Visualization; Unsupervised 3D shape retrieval; cross-domain representation; domain adaptation

Funding

  1. National Natural Science Foundation of China [U21B2024]
  2. China Postdoctoral Science Foundation [2022M712369]
  3. Baidu Pinecone Program

Ask authors/readers for more resources

In this paper, an unsupervised method for 2D image-based 3D shape retrieval is proposed, which achieves discriminative representation learning and domain adaptation through multi-view guided self-supervised feature learning and auxiliary domain alignment. The method achieves competitive performance in the unsupervised 2D image-based 3D shape retrieval task.
Unsupervised 2D image-based 3D shape retrieval aims to match the similar 3D unlabeled shapes when given a 2D labeled sample. Although a lot of methods have made a certain degree of progress, the performance of this task is still restricted due to the lack of target labels resulting in tremendous domain gap. In this paper, we aim to explore the discriminative representation of the unlabeled target 3D shapes and facilitate the procedure of domain adaptation by taking full advantage of multi-view information. To achieve the above goals, we propose an effective self-supervised auxiliary domain alignment (SADA) for unsupervised 2D image-based 3D shape retrieval. SADA mainly contains multi-view guided self-supervised feature learning and two auxiliary domain alignments, including intermediate domain alignment and multi-domain alignment. Firstly, we group multiple views of each 3D shape into two sub-target domains based on the view similarities and regard each other as the constraint to optimize the feature learning in an unsupervised manner. To reduce the difficulty of directly aligning the domain discrepancy, we combine the source labeled samples and target samples (pseudo labels) with the same category to generate an intermediate domain, which translates the source-target alignment into source-intermediate and intermediate-target alignments. Moreover, to explore the inner characteristics of target 3D shapes and provide more clues for better adaptation, multi-domain alignment is proposed to convert the source and single target domain alignment to the source and multiple target domain (one target domain and two sub-target domains) alignments. The adversarial training and semantic alignment are employed to fully excavate the relations between source domain and multiple target domains. Experiments on two challenging datasets show that the proposed method achieves competing performance in the unsupervised 2D image-based 3D shape retrieval task.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available