Few-shot 3D Point Cloud Semantic Segmentation
- URL: http://arxiv.org/abs/2006.12052v2
- Date: Mon, 29 Mar 2021 05:55:06 GMT
- Title: Few-shot 3D Point Cloud Semantic Segmentation
- Authors: Na Zhao, Tat-Seng Chua, Gim Hee Lee
- Abstract summary: We propose a novel attention-aware multi-prototype transductive few-shot point cloud semantic segmentation method.
Our proposed method shows significant and consistent improvements compared to baselines in different few-shot point cloud semantic segmentation settings.
- Score: 138.80825169240302
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Many existing approaches for 3D point cloud semantic segmentation are fully
supervised. These fully supervised approaches heavily rely on large amounts of
labeled training data that are difficult to obtain and cannot segment new
classes after training. To mitigate these limitations, we propose a novel
attention-aware multi-prototype transductive few-shot point cloud semantic
segmentation method to segment new classes given a few labeled examples.
Specifically, each class is represented by multiple prototypes to model the
complex data distribution of labeled points. Subsequently, we employ a
transductive label propagation method to exploit the affinities between labeled
multi-prototypes and unlabeled points, and among the unlabeled points.
Furthermore, we design an attention-aware multi-level feature learning network
to learn the discriminative features that capture the geometric dependencies
and semantic correlations between points. Our proposed method shows significant
and consistent improvements compared to baselines in different few-shot point
cloud semantic segmentation settings (i.e., 2/3-way 1/5-shot) on two benchmark
datasets. Our code is available at https://github.com/Na-Z/attMPTI.
Related papers
- FreePoint: Unsupervised Point Cloud Instance Segmentation [72.64540130803687]
We propose FreePoint, for underexplored unsupervised class-agnostic instance segmentation on point clouds.
We represent point features by combining coordinates, colors, and self-supervised deep features.
Based on the point features, we segment point clouds into coarse instance masks as pseudo labels, which are used to train a point cloud instance segmentation model.
arXiv Detail & Related papers (2023-05-11T16:56:26Z) - Few-Shot 3D Point Cloud Semantic Segmentation via Stratified
Class-Specific Attention Based Transformer Network [22.9434434107516]
We develop a new multi-layer transformer network for few-shot point cloud semantic segmentation.
Our method achieves the new state-of-the-art performance, with 15% less inference time, over existing few-shot 3D point cloud segmentation models.
arXiv Detail & Related papers (2023-03-28T00:27:54Z) - LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds [62.49198183539889]
We propose a label-efficient semantic segmentation pipeline for outdoor scenes with LiDAR point clouds.
Our method co-designs an efficient labeling process with semi/weakly supervised learning.
Our proposed method is even highly competitive compared to the fully supervised counterpart with 100% labels.
arXiv Detail & Related papers (2022-10-14T19:13:36Z) - Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype
Learning [37.76664203157892]
A fundamental challenge here lies in the large intra-class variations of local geometric structure, resulting in subclasses within a semantic class.
We leverage this intuition and opt for maintaining an individual classifier for each subclass.
Our hypothesis is also verified given the consistent discovery of semantic subclasses at no cost of additional annotations.
arXiv Detail & Related papers (2022-05-06T11:07:36Z) - Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level
Supervision [65.19589997822155]
We introduce a neural architecture, termed Box2Seg, to learn point-level semantics of 3D point clouds with bounding box-level supervision.
We show that the proposed network can be trained with cheap, or even off-the-shelf bounding box-level annotations and subcloud-level tags.
arXiv Detail & Related papers (2022-01-09T09:07:48Z) - Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds [59.63231842439687]
We train a semantic point cloud segmentation network with only a small portion of points being labeled.
We propose a cross-sample feature reallocating module to transfer similar features and therefore re-route the gradients across two samples.
Our weakly supervised method with only 10% and 1% of labels can produce compatible results with the fully supervised counterpart.
arXiv Detail & Related papers (2021-07-23T14:34:57Z) - SCSS-Net: Superpoint Constrained Semi-supervised Segmentation Network
for 3D Indoor Scenes [6.3364439467281315]
We propose a superpoint constrained semi-supervised segmentation network for 3D point clouds, named as SCSS-Net.
Specifically, we use the pseudo labels predicted from unlabeled point clouds for self-training, and the superpoints produced by geometry-based and color-based Region Growing algorithms are combined to modify and delete pseudo labels with low confidence.
arXiv Detail & Related papers (2021-07-08T04:43:21Z) - One Thing One Click: A Self-Training Approach for Weakly Supervised 3D
Semantic Segmentation [78.36781565047656]
We propose "One Thing One Click," meaning that the annotator only needs to label one point per object.
We iteratively conduct the training and label propagation, facilitated by a graph propagation module.
Our results are also comparable to those of the fully supervised counterparts.
arXiv Detail & Related papers (2021-04-06T02:27:25Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.