Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection
Preprint
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.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Rethinking Pseudo Labels for Semi-supervised Object DetectionProceedings of the AAAI Conference on Artificial Intelligence, 2022
- Part-Aware Data Augmentation for 3D Object Detection in Point Cloud2021
- From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation NetworkIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- SECOND: Sparsely Embedded Convolutional DetectionSensors, 2018