• Corpus ID: 231632271

Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approach

@article{Shi2021LabelEfficientPC,
  title={Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approach},
  author={Xian Shi and Xun Xu and Ke Chen and Lile Cai and Chuan-Sheng Foo and Kui Jia},
  journal={ArXiv},
  year={2021},
  volume={abs/2101.06931}
}
Semantic segmentation of 3D point clouds relies on training deep models with a large amount of labeled data. However, labeling 3D point clouds is expensive, thus smart approach towards data annotation, a.k.a. active learning is essential to label-efficient point cloud segmentation. In this work, we first propose a more realistic annotation counting scheme so that a fair benchmark is possible. To better exploit labeling budget, we adopt a super-point based active learning strategy where we make… 

Recognizing Predictive Substructures with Subgraph Information Bottleneck

A novel subgraph information bottleneck (SIB) framework to recognize a predictive yet compressed subgraph to get rid of the noise and redundancy and obtain the interpretable part of the graph and theoretically prove the error bound of the estimation scheme for mutual information and the noise-invariant nature of IB-subgraph.

LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds

Evaluated on the SemanticKITTI and the nuScenes datasets, it is shown that the proposed method outperforms existing label-efficient methods and is even highly competitive compared to the fully supervised counterpart with 100% labels.

LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds

Evaluated on the SemanticKITTI and the nuScenes datasets, the proposed method outperforms existing label-efficient methods and is even highly competitive compared to the fully supervised counterpart with 100% labels.

LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation

. This supplementary document is organized as follows: more detail about the LiDAL implementation. 3 enumerates segmentation

Supervoxel-based and Cost-Effective Active Learning for Point Cloud Semantic Segmentation

A supervoxel-based and cost-effective active learning pipeline which aims to select only uncertain and diverse segmented regions for annotation and to leverage point cloud intensity when calculating the segmented region information for encouraging region diversity is proposed.

Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentation

This paper introduces a method for weakly supervised segmentation of 3D scenes that combines self-training with active learning, and demonstrates that this approach leads to an effective method that provides improvements in scene segmentation over previous works and baselines, while requiring only a small number of user annotations.

Learning indoor point cloud semantic segmentation from image-level labels

A weakly supervised framework for semantic segmentation on indoor point clouds is introduced that uses image-level weak labels that only indicate the classes that appeared in the rendered images of point clouds.

HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive Regularization

This work proposes a novel hybrid contrastive regularization (HybridCR) framework in weakly-supervised setting, which obtains competitive performance compared to its fully- supervised counterpart, and is the first framework to leverage both point consistency and employ contrastiveRegularization with pseudo labeling in an end-to-end manner.

Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learning

Experiments on weakly supervised 3D point cloud segmentation tasks validate the efficacy of proposed method in particular at low-label regime and given the consistent discovery of semantic subclasses at no cost of additional annotations.

PointMatch: A Consistency Training Framework for Weakly SupervisedSemantic Segmentation of 3D Point Clouds

This work proposes a novel framework, PointMatch, that stands on both data and label, by applying consistency regularization to sufficiently probe information from data itself and leveraging weak labels as assistance at the same time, which achieves the state-of-theart performance under various weakly-supervised schemes on both ScanNet-v2 and S3DIS datasets.

References

SHOWING 1-10 OF 29 REFERENCES

Weakly Supervised Semantic Point Cloud Segmentation: Towards 10× Fewer Labels

This work proposes a weakly supervised point cloud segmentation approach which requires only a tiny fraction of points to be labelled in the training stage and can produce results that are close to and sometimes even better than its fully supervised counterpart with 10× fewer labels.

Multi-Path Region Mining for Weakly Supervised 3D Semantic Segmentation on Point Clouds

This paper introduces a multi-path region mining module to generate pseudo point-level labels from a classification network trained with weak labels, and uses the point- level pseudo label to train a point cloud segmentation network in a fully supervised manner.

Weakly Supervised 3D Object Detection from Point Clouds

VS3D, a framework for weakly supervised 3D object detection from point clouds without using any ground truth 3D bounding box for training, is proposed and an unsupervised 3D proposal module that generates object proposals by leveraging normalized point cloud densities is introduced.

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.

PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding

This work aims at facilitating research on 3D representation learning by selecting a suite of diverse datasets and tasks to measure the effect of unsupervised pre-training on a large source set of 3D scenes and achieving improvement over recent best results in segmentation and detection across 6 different benchmarks.

ViewAL: Active Learning With Viewpoint Entropy for Semantic Segmentation

This work introduces a new viewpoint entropy formulation, which is the basis of a novel active learning strategy for semantic segmentation that exploits viewpoint consistency in multi-view datasets and proposes uncertainty computations on a superpixel level, which exploits inherently localized signal in the segmentation task, directly lowering the annotation costs.

Self-Supervised Deep Learning on Point Clouds by Reconstructing Space

This work proposes a self-supervised learning task for deep learning on raw point cloud data in which a neural network is trained to reconstruct point clouds whose parts have been randomly rearranged, and demonstrates that pre-training with this method before supervised training improves the performance of state-of-the-art models and significantly improves sample efficiency.

Deep Hough Voting for 3D Object Detection in Point Clouds

This work proposes VoteNet, an end-to-end 3D object detection network based on a synergy of deep point set networks and Hough voting that achieves state-of-the-art 3D detection on two large datasets of real 3D scans, ScanNet and SUN RGB-D with a simple design, compact model size and high efficiency.

Dynamic Graph CNN for Learning on Point Clouds

This work proposes a new neural network module suitable for CNN-based high-level tasks on point clouds, including classification and segmentation called EdgeConv, which acts on graphs dynamically computed in each layer of the network.

PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding

  • Kaichun MoShilin Zhu Hao Su
  • Computer Science
    2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
This work presents PartNet, a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information, and proposes a baseline method for part instance segmentation that is superior performance over existing methods.