PartCom: Part Composition Learning for 3D Open-Set Recognition

11/20/2022
by   Weng Tingyu, et al.
0

3D recognition is the foundation of 3D deep learning in many emerging fields, such as autonomous driving and robotics.Existing 3D methods mainly focus on the recognition of a fixed set of known classes and neglect possible unknown classes during testing. These unknown classes may cause serious accidents in safety-critical applications, i.e. autonomous driving. In this work, we make a first attempt to address 3D open-set recognition (OSR) so that a classifier can recognize known classes as well as be aware of unknown classes. We analyze open-set risks in the 3D domain and point out the overconfidence and under-representation problems that make existing methods perform poorly on the 3D OSR task. To resolve above problems, we propose a novel part prototype-based OSR method named PartCom. We use part prototypes to represent a 3D shape as a part composition, since a part composition can represent the overall structure of a shape and can help distinguish different known classes and unknown ones. Then we formulate two constraints on part prototypes to ensure their effectiveness. To reduce open-set risks further, we devise a PUFS module to synthesize unknown features as representatives of unknown samples by mixing up part composite features of different classes. We conduct experiments on three kinds of 3D OSR tasks based on both CAD shape dataset and scan shape dataset. Extensive experiments show that our method is powerful in classifying known classes and unknown ones and can attain much better results than SOTA baselines on all 3D OSR tasks. The project will be released.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/21/2021

Spatial Location Constraint Prototype Loss for Open Set Recognition

One of the challenges in pattern recognition is open set recognition. Co...
research
07/18/2022

Semantic Novelty Detection via Relational Reasoning

Semantic novelty detection aims at discovering unknown categories in the...
research
05/07/2021

Video Class Agnostic Segmentation with Contrastive Learning for Autonomous Driving

Semantic segmentation in autonomous driving predominantly focuses on lea...
research
06/28/2023

OpenNDD: Open Set Recognition for Neurodevelopmental Disorders Detection

Neurodevelopmental disorders (NDDs) are a highly prevalent group of diso...
research
10/21/2021

Evaluation of Various Open-Set Medical Imaging Tasks with Deep Neural Networks

The current generation of deep neural networks has achieved close-to-hum...
research
04/19/2021

Conditional Variational Capsule Network for Open Set Recognition

In open set recognition, a classifier has to detect unknown classes that...
research
05/18/2021

Exemplar-Based Open-Set Panoptic Segmentation Network

We extend panoptic segmentation to the open-world and introduce an open-...

Please sign up or login with your details

Forgot password? Click here to reset