One Class One Click: Quasi Scene-level Weakly Supervised Point Cloud Semantic Segmentation with Active Learning

11/23/2022
by   Puzuo Wang, et al.
0

Reliance on vast annotations to achieve leading performance severely restricts the practicality of large-scale point cloud semantic segmentation. For the purpose of reducing data annotation costs, effective labeling schemes are developed and contribute to attaining competitive results under weak supervision strategy. Revisiting current weak label forms, we introduce One Class One Click (OCOC), a low cost yet informative quasi scene-level label, which encapsulates point-level and scene-level annotations. An active weakly supervised framework is proposed to leverage scarce labels by involving weak supervision from global and local perspectives. Contextual constraints are imposed by an auxiliary scene classification task, respectively based on global feature embedding and point-wise prediction aggregation, which restricts the model prediction merely to OCOC labels. Furthermore, we design a context-aware pseudo labeling strategy, which effectively supplement point-level supervisory signals. Finally, an active learning scheme with a uncertainty measure - temporal output discrepancy is integrated to examine informative samples and provides guidance on sub-clouds query, which is conducive to quickly attaining desirable OCOC annotations and reduces the labeling cost to an extremely low extent. Extensive experimental analysis using three LiDAR benchmarks collected from airborne, mobile and ground platforms demonstrates that our proposed method achieves very promising results though subject to scarce labels. It considerably outperforms genuine scene-level weakly supervised methods by up to 25% in terms of average F1 score and achieves competitive results against full supervision schemes. On terrestrial LiDAR dataset - Semantics3D, using approximately 2‱ of labels, our method achieves an average F1 score of 85.2%, which increases by 11.58% compared to the baseline model.

READ FULL TEXT

page 5

page 6

page 7

page 9

page 11

page 12

page 14

research
10/04/2021

A new weakly supervised approach for ALS point cloud semantic segmentation

While there are novel point cloud semantic segmentation schemes that con...
research
03/29/2020

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

Point clouds provide intrinsic geometric information and surface context...
research
05/05/2021

Weakly Supervised Pseudo-Label assisted Learning for ALS Point Cloud Semantic Segmentation

Competitive point cloud semantic segmentation results usually rely on a ...
research
08/09/2023

Discrepancy-based Active Learning for Weakly Supervised Bleeding Segmentation in Wireless Capsule Endoscopy Images

Weakly supervised methods, such as class activation maps (CAM) based, ha...
research
09/16/2022

Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learning

Weakly supervised point cloud semantic segmentation methods that require...
research
10/06/2022

Adaptive Ranking-based Sample Selection for Weakly Supervised Class-imbalanced Text Classification

To obtain a large amount of training labels inexpensively, researchers h...
research
11/02/2022

Hypergraph Convolutional Network based Weakly Supervised Point Cloud Semantic Segmentation with Scene-Level Annotations

Point cloud segmentation with scene-level annotations is a promising but...

Please sign up or login with your details

Forgot password? Click here to reset