Abstract | ||
---|---|---|
Geometric deep learning is increasingly important thanks to the popularity of 3D sensors. Inspired by the recent advances in NLP domain, the self-attention transformer is introduced to consume the point clouds. We develop Point Attention Transformers (PATs), using a parameter-efficient Group Shuffle Attention (GSA) to replace the costly Multi-Head Attention. We demonstrate its ability to process size-varying inputs, and prove its permutation equivariance. Besides, prior work uses heuristics dependence on the input data (e.g., Furthest Point Sampling) to hierarchically select subsets of input points. Thereby, we for the first time propose an end-to-end learnable and taskagnostic sampling operation, named Gumbel Subset Sampling (GSS), to select a representative subset of input points. Equipped with Gumbel-Softmax, it produces a "soft" continuous subset in training phase, and a "hard" discrete subset in test phase. By selecting representative subsets in a hierarchical fashion, the networks learn a stronger representation of the input sets with lower computation cost. Experiments on classification and segmentation benchmarks show the effectiveness and efficiency of our methods. Furthermore, we propose a novel application, to process event camera stream as point clouds, and achieve a state-of-the-art performance on DVS128 Gesture Dataset. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/CVPR.2019.00344 | 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) |
Field | DocType | Volume |
Segmentation,Computer science,Permutation,Gumbel distribution,Theoretical computer science,Heuristics,Artificial intelligence,Sampling (statistics),Deep learning,Point cloud,Machine learning,Computation | Journal | abs/1904.03375 |
ISSN | Citations | PageRank |
1063-6919 | 10 | 0.46 |
References | Authors | |
0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiancheng Yang | 1 | 20 | 6.74 |
Qiang Zhang | 2 | 24 | 1.29 |
Bingbing Ni | 3 | 1421 | 82.90 |
Linguo Li | 4 | 10 | 0.80 |
Jinxian Liu | 5 | 15 | 1.54 |
Mengdie Zhou | 6 | 10 | 0.46 |
Qi Tian | 7 | 6443 | 331.75 |