Corpus ID: 236428749

ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation

  title={ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation},
  author={Tsung-Han Wu and Yueh-Cheng Liu and Yu-Kai Huang and Hsin-Ying Lee and Hung-Ting Su and Ping-Chia Huang and Winston H. Hsu},
Despite the success of deep learning on supervised point cloud semantic segmentation, obtaining large-scale pointby-point manual annotations is still a significant challenge. To reduce the huge annotation burden, we propose a Region-based and Diversity-aware Active Learning (ReDAL), a general framework for many deep learning approaches, aiming to automatically select only informative and diverse sub-scene regions for label acquisition. Observing that only a small portion of annotated regions… Expand


A segment based active learning strategy to assess the informativeness of samples is proposed, which uses 40% of the whole training dataset to achieve a mean IoU of 75.2% which is 99.1%" of the accuracy in mIoU obtained from the model trained on the full dataset. Expand
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. Expand
Weakly Supervised Semantic Point Cloud Segmentation: Towards 10× Fewer Labels
  • Xun Xu, Gim Hee Lee
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
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, made possible by learning gradient approximation and exploitation of additional spatial and color smoothness constraints. Expand
Semantic Labeling of Mobile LiDAR Point Clouds via Active Learning and Higher Order MRF
This paper introduces an active learning method that avoids annotating the whole point cloud scenes by iteratively annotating a small portion of unlabeled supervoxels and creating a minimal manually annotated training set. Expand
SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud
This work introduces a new model SqueezeSegV2, which is more robust against dropout noises in LiDAR point cloud and therefore achieves significant accuracy improvement, and a domain-adaptation training pipeline consisting of three major components: learned intensity rendering, geodesic correlation alignment, and progressive domain calibration. Expand A new Large-scale Point Cloud Classification Benchmark
It is hoped this http URL will pave the way for deep learning methods in 3D point cloud labelling to learn richer, more general 3D representations, and first submissions after only a few months indicate that this might indeed be the case. Expand
ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes
This work introduces ScanNet, an RGB-D video dataset containing 2.5M views in 1513 scenes annotated with 3D camera poses, surface reconstructions, and semantic segmentations, and shows that using this data helps achieve state-of-the-art performance on several 3D scene understanding tasks. Expand
Graph Attention Convolution for Point Cloud Semantic Segmentation
A novel graph attention convolution, whose kernels can be dynamically carved into specific shapes to adapt to the structure of an object, which can capture the structured features of point clouds for fine-grained segmentation and avoid feature contamination between objects. Expand
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. Expand
Cost-Effective Active Learning for Deep Image Classification
This paper proposes a novel active learning (AL) framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner and incorporates deep convolutional neural networks into AL. Expand