3D2SeqViews: Aggregating Sequential Views for 3D Global Feature Learning by CNN With Hierarchical Attention Aggregation

By Zhizhong Han, Hong-Lei Lu, Zhenbao Liu, Chi-Man Vong, Yu-Shen Liu, Matthias Zwicker, Junwei Han, C. L. Philip Chen. 2019

180 citations recorded by the source corpus.

Learning 3D global features by aggregating multiple views is important. Pooling is widely used to aggregate views in deep learning models. However, pooling disregards a lot of content information within views and the spatial relationship among the views, which limits the discriminability of learned features. To resolve this issue, 3D to Sequential Views (3D2SeqViews) is proposed to more effectively aggregate the sequential views using convolutional neural networks with a novel hierarchical attention aggregation. Specifically, the content information within each view is first encoded. Then, the encoded view content information and the sequential spatiality among the views are simultaneously aggregated by the hierarchical attention aggregation, where view-level attention and class-level attention are proposed to hierarchically weight sequential views and shape classes. View-level attention is learned to indicate how much attention is paid to each view by each shape class, which subsequently weights sequential views through a novel recursive view integration. Recursive view integration learns the semantic meaning of view sequence, which is robust to the first view position. Furthermore, class-level attention is introduced to describe how much attention is paid to each shape class, which innovatively employs the discriminative ability of the fine-tuned network. 3D2SeqViews learns more discriminative features than the state-of-the-art, which leads to the outperforming results in shape classification and retrieval under three large-scale benchmarks.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Geology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Peng Xiang
2. Xin Wen
3. Wen Zheng
4. Yan-Pei Cao
5. Zhizhong Han
6. Pengfei Wan
7. Yu-Shen Liu

In Computer Vision and Pattern Recognition

1. Zhizhong Han
2. Pengfei Wan
3. Yu-Shen Liu

In Geology

1. Zhizhong Han
2. Yu-Shen Liu

Citations in the corpus

• SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer (2021, background): “(2) Deep learning [28, 12, 15, 23, 19, 17, 16, 22, 50, 51] based methods [27, 46, 4, 8, 37, 25, 24], however, learn to predict a complete shape based on the learned prior from the training data.”
• View-GCN: View-Based Graph Convolutional Network for 3D Shape Analysis (2020, unknown): “3D2SeqViews[19], Se-qViews2SeqLabels [20], VERAM [8], and Ma et al. [34] all exploit relations on sequential views.”