Publications
Detailed Information
PointMixer: MLP-Mixer for Point Cloud Understanding
Cited 15 time in
Web of Science
Cited 19 time in Scopus
- Authors
- Issue Date
- 2022
- Publisher
- Springer Verlag
- Citation
- Lecture Notes in Computer Science, Vol.13687, pp.620-640
- Abstract
- MLP-Mixer has newly appeared as a new challenger against the realm of CNNs and Transformer. Despite its simplicity compared to Transformer, the concept of channel-mixing MLPs and token-mixing MLPs achieves noticeable performance in image recognition tasks. Unlike images, point clouds are inherently sparse, unordered and irregular, which limits the direct use of MLP-Mixer for point cloud understanding. To overcome these limitations, we propose PointMixer, a universal point set operator that facilitates information sharing among unstructured 3D point cloud. By simply replacing token-mixing MLPs with Softmax function, PointMixer can mix features within/between point sets. By doing so, PointMixer can be broadly used for intra-set, inter-set, and hierarchical-set mixing. We demonstrate that various channel-wise feature aggregation in numerous point sets is better than self-attention layers or dense token-wise interaction in a view of parameter efficiency and accuracy. Extensive experiments show the competitive or superior performance of PointMixer in semantic segmentation, classification, and reconstruction against Transformer-based methods.
- ISSN
- 0302-9743
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.