Scribble-Supervised LiDAR Semantic Segmentation (2022-03-16T00:00:00.000000Z)

TL;DR

This paper proposes using scribbles to annotate LiDAR point clouds and releases ScribbleKITTI, the first scribble-annotated dataset for LiDar semantic segmentation, and presents a pipeline to reduce the performance gap that arises when using such weak annotations.

Abstract

Densely annotating LiDAR point clouds remains too expensive and time-consuming to keep up with the ever growing volume of data. While current literature focuses on fully-supervised performance, developing efficient methods that take advantage of realistic weak supervision have yet to be explored. In this paper, we propose using scribbles to annotate LiDAR point clouds and release ScribbleKITTI, the first scribble-annotated dataset for LiDAR semantic segmentation. Furthermore, we present a pipeline to reduce the performance gap that arises when using such weak annotations. Our pipeline comprises of three stand-alone contributions that can be combined with any LiDAR semantic segmentation model to achieve up to 95.7% of the fully-supervised performance while using only 8% labeled points. Our scribble annotations and code are available at github.com/ouenal/scribblekitti.

Authors

L. Gool

68 papers

Dengxin Dai

12 papers

Ozan Unal

1 papers

TL;DR

Abstract

Authors

References59 items

Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation

Perturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud Semantic Segmentation

Weakly Supervised Segmentation of COVID19 Infection with Scribble Annotation on CT Images

Seminar Learning for Click-Level Weakly Supervised Semantic Segmentation

Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation

PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training

SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network

Self-Supervised Learning for Semi-Supervised Temporal Action Proposal

RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation

Weakly-Supervised teacher-Student network for liver tumor segmentation from non-enhanced images

Unbiased Teacher for Semi-Supervised Object Detection

AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentation

Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation

Multi Projection Fusion for Real-time Semantic Segmentation of 3D LiDAR Point Clouds

Improving Point Cloud Semantic Segmentation by Learning 3D Object Detection

Scribble-Based 3D Shape Segmentation via Weakly-Supervised Learning

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

KPRNet: Improving projection-based LiDAR semantic segmentation

Weakly Supervised 3D Object Detection from Lidar Point Cloud

Scribble2Label: Scribble-Supervised Cell Segmentation via Self-Generating Pseudo-Labels with Consistency

Rethinking Pre-training and Self-training

SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

SalsaNext: Fast, Uncertainty-Aware Semantic Segmentation of LiDAR Point Clouds

3D-MiniNet: Learning a 2D Representation From Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning

Structured Consistency Loss for semi-supervised semantic segmentation

RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds

Self-Training With Noisy Student Improves ImageNet Classification

RangeNet ++: Fast and Accurate LiDAR Semantic Segmentation

Weakly-Supervised Semantic Segmentation with Mean Teacher Learning

Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning

MixMatch: A Holistic Approach to Semi-Supervised Learning

4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks

KPConv: Flexible and Deformable Convolution for Point Clouds

SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences

Semi-Supervised Brain Lesion Segmentation with an Adapted Mean Teacher Model

SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud

Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-training

Learning to Segment Medical Images with Scribble-Supervision Alone

Deep semi-supervised segmentation with weight-averaged consistency targets

Learning Pixel-Level Semantic Affinity with Image-Level Supervision for Weakly Supervised Semantic Segmentation

On Regularized Losses for Weakly-supervised CNN Segmentation

SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results

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

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation

Constrained Convolutional Neural Networks for Weakly Supervised Segmentation

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation

Vision meets robotics: The KITTI dataset

Acceleration of stochastic approximation by averaging

Semi-supervised point cloud segmentation using self-training with label confidence prediction

Deep FusionNet for Point Cloud Semantic Segmentation

Scribble Supervised Annotation Algorithms of Panoptic Segmentation for Autonomous Driving

Deep semisupervised segmentation with weight-averaged consistency targets. In Deep learning in medical image analysis and multimodal learning for clinical decision support

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names