SOAP: Cross-sensor Domain Adaptation for 3D Object Detection Using Stationary Object Aggregation Pseudo-labelling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Chengjie, Abdelzad, Vahdat, Sedwards, Sean, Czarnecki, Krzysztof
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929203829538816
author Huang, Chengjie
Abdelzad, Vahdat
Sedwards, Sean
Czarnecki, Krzysztof
author_facet Huang, Chengjie
Abdelzad, Vahdat
Sedwards, Sean
Czarnecki, Krzysztof
contents We consider the problem of cross-sensor domain adaptation in the context of LiDAR-based 3D object detection and propose Stationary Object Aggregation Pseudo-labelling (SOAP) to generate high quality pseudo-labels for stationary objects. In contrast to the current state-of-the-art in-domain practice of aggregating just a few input scans, SOAP aggregates entire sequences of point clouds at the input level to reduce the sensor domain gap. Then, by means of what we call quasi-stationary training and spatial consistency post-processing, the SOAP model generates accurate pseudo-labels for stationary objects, closing a minimum of 30.3% domain gap compared to few-frame detectors. Our results also show that state-of-the-art domain adaptation approaches can achieve even greater performance in combination with SOAP, in both the unsupervised and semi-supervised settings.
format Preprint
id arxiv_https___arxiv_org_abs_2401_04230
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SOAP: Cross-sensor Domain Adaptation for 3D Object Detection Using Stationary Object Aggregation Pseudo-labelling
Huang, Chengjie
Abdelzad, Vahdat
Sedwards, Sean
Czarnecki, Krzysztof
Computer Vision and Pattern Recognition
We consider the problem of cross-sensor domain adaptation in the context of LiDAR-based 3D object detection and propose Stationary Object Aggregation Pseudo-labelling (SOAP) to generate high quality pseudo-labels for stationary objects. In contrast to the current state-of-the-art in-domain practice of aggregating just a few input scans, SOAP aggregates entire sequences of point clouds at the input level to reduce the sensor domain gap. Then, by means of what we call quasi-stationary training and spatial consistency post-processing, the SOAP model generates accurate pseudo-labels for stationary objects, closing a minimum of 30.3% domain gap compared to few-frame detectors. Our results also show that state-of-the-art domain adaptation approaches can achieve even greater performance in combination with SOAP, in both the unsupervised and semi-supervised settings.
title SOAP: Cross-sensor Domain Adaptation for 3D Object Detection Using Stationary Object Aggregation Pseudo-labelling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.04230