Learning from Mistakes: Self-Regularizing Hierarchical Semantic Representations in Point Cloud Segmentation

by   Elena Camuffo, et al.
Università di Padova

Recent advances in autonomous robotic technologies have highlighted the growing need for precise environmental analysis. LiDAR semantic segmentation has gained attention to accomplish fine-grained scene understanding by acting directly on raw content provided by sensors. Recent solutions showed how different learning techniques can be used to improve the performance of the model, without any architectural or dataset change. Following this trend, we present a coarse-to-fine setup that LEArns from classification mistaKes (LEAK) derived from a standard model. First, classes are clustered into macro groups according to mutual prediction errors; then, the learning process is regularized by: (1) aligning class-conditional prototypical feature representation for both fine and coarse classes, (2) weighting instances with a per-class fairness index. Our LEAK approach is very general and can be seamlessly applied on top of any segmentation architecture; indeed, experimental results showed that it enables state-of-the-art performances on different architectures, datasets and tasks, while ensuring more balanced class-wise results and faster convergence.


page 1

page 5

page 6


Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data

During the last few years, continual learning (CL) strategies for image ...

Number-Adaptive Prototype Learning for 3D Point Cloud Semantic Segmentation

3D point cloud semantic segmentation is one of the fundamental tasks for...

CoFi: Coarse-to-Fine ICP for LiDAR Localization in an Efficient Long-lasting Point Cloud Map

LiDAR odometry and localization has attracted increasing research intere...

Impact of Ground Truth Annotation Quality on Performance of Semantic Image Segmentation of Traffic Conditions

Preparation of high-quality datasets for the urban scene understanding i...

Coarse-to-fine volumetric segmentation of teeth in Cone-Beam CT

We consider the problem of localizing and segmenting individual teeth in...

Hierarchical Dense Correlation Distillation for Few-Shot Segmentation

Few-shot semantic segmentation (FSS) aims to form class-agnostic models ...

SEGCloud: Semantic Segmentation of 3D Point Clouds

3D semantic scene labeling is fundamental to agents operating in the rea...

Please sign up or login with your details

Forgot password? Click here to reset