HMTN: Hierarchical Multi-scale Transformer Network for 3D Shape Recognition

Yue Zhao, Weizhi Nie, Zan Gao, Anan LiuACM Multimedia 2022 · OpenReview

Abstract

As an important field of multimedia, 3D shape recognition has attracted much research attention in recent years. Various approaches have been proposed, within which the multiview-based methods show their promising performances. In general, an effective 3D shape recognition algorithm should take both the multiview local and global visual information into consideration, and explore the inherent properties of generated 3D descriptors to guarantee the performance of feature alignment in the common space. To tackle these issues, we propose a novel Hierarchical Multi-scale Transformer Network (HMTN) for the 3D shape recognition task. In HMTN, we propose a multi-level regional transformer (MLRT) module for shape descriptor generation. MLRT includes two branches that aim to extract the intra-view local characteristics by modeling region-wise dependencies and give the supervision of multiview global information under different granularities. Specifically, MLRT can comprehensively consider the relations of different regions and focus on the discriminative parts, which improves the effectiveness of the learned descriptors. Finally, we adopt the cross-granularity contrastive learning (CCL) mechanism for shape descriptor alignment in the common space. It can explore and utilize the cross-granularity semantic correlation to guide the descriptor extraction process while performing the instance alignment based on the category information. We evaluate the proposed network on several public benchmarks, and HMTN achieves competitive performance compared with the state-of-the-art (SOTA) methods.
BibTeX
@inproceedings{zhao2022hmtn,
  author = {Yue Zhao and Weizhi Nie and Zan Gao and Anan Liu},
  title = {{HMTN: Hierarchical Multi-scale Transformer Network for 3D Shape Recognition}},
  booktitle = {ACM Multimedia},
  year = {2022},
  url = {https://openreview.net/forum?id=3yRQZo31uF},
}

Loading related content...

Figure