Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection
Cheng-Ju Ho (National Yang Ming Chiao Tung University),* Chen-Hsuan Tai (National Yang Ming Chiao Tung University), Yi-Hsuan Tsai (Google), Yen-Yu Lin (National Yang Ming Chiao Tung University), Ming-Hsuan Yang (University of California at Merced)
The 33rd British Machine Vision Conference
Abstract
Semi-supervised object detection is important for 3D scene understanding because obtaining large-scale 3D bounding box annotations on point clouds is time-consuming and labor-intensive. Existing semi-supervised methods usually employ teacher-student knowledge distillation together with an augmentation strategy to leverage unlabeled point clouds. However, these methods adopt global augmentation with scene-level transformations and hence are sub-optimal for instance-level object detection. In this work, we propose an object-level point augmentor (OPA) that performs local transformations for semi-supervised 3D object detection. In this way, the resultant augmentor is derived to emphasize object instances rather than irrelevant backgrounds, making the augmented data more useful for object detector training. Extensive experiments on the ScanNet and SUN RGB-D datasets show that the proposed OPA performs favorably against the state-of-the-art methods under various experimental settings. The source code will be available at https://github.com/nomiaro/OPA.Video
Citation
@inproceedings{Ho_2022_BMVC,
author = {Cheng-Ju Ho and Chen-Hsuan Tai and Yi-Hsuan Tsai and Yen-Yu Lin and Ming-Hsuan Yang},
title = {Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0185.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by