Multi-Path Region Mining for Weakly Supervised 3D Semantic Segmentation on Point Clouds
- 1 June 2020
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4383-4392
- https://doi.org/10.1109/cvpr42600.2020.00444
Abstract
Point clouds provide intrinsic geometric information and surface context for scene understanding. Existing methods for point cloud segmentation require a large amount of fully labeled data. Using advanced depth sensors, collection of large scale 3D dataset is no longer a cumbersome process. However, manually producing point-level label on the large scale dataset is time and labor-intensive. In this paper, we propose a weakly supervised approach to predict point-level results using weak labels on 3D point clouds. We introduce our multi-path region mining module to generate pseudo point-level labels from a classification network trained with weak labels. It mines the localization cues for each class from various aspects of the network feature using different attention modules. Then, we use the point-level pseudo label to train a point cloud segmentation network in a fully supervised manner. To the best of our knowledge, this is the first method that uses cloud-level weak labels on raw 3D space to train a point cloud semantic segmentation network. In our setting, the 3D weak labels only indicate the classes that appeared in our input sample. We discuss both scene- and subcloud-level weakly labels on raw 3D point cloud data and perform in-depth experiments on them. On ScanNet dataset, our result trained with subcloud-level labels is compatible with some fully supervised methods.Keywords
This publication has 29 references indexed in Scilit:
- Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation ApproachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Simple Does It: Weakly Supervised Instance and Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor ScenesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Pyramid Scene Parsing NetworkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- What’s the Point: Semantic Segmentation with Point SupervisionPublished by Springer Science and Business Media LLC ,2016
- Deep Residual Learning for Image RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Learning Deep Features for Discriminative LocalizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Multi-view Convolutional Neural Networks for 3D Shape RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- VoxNet: A 3D Convolutional Neural Network for real-time object recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015