Semi-supervised 3D Object Detection with Proficient Teachers

by   Junbo Yin, et al.

Dominated point cloud-based 3D object detectors in autonomous driving scenarios rely heavily on the huge amount of accurately labeled samples, however, 3D annotation in the point cloud is extremely tedious, expensive and time-consuming. To reduce the dependence on large supervision, semi-supervised learning (SSL) based approaches have been proposed. The Pseudo-Labeling methodology is commonly used for SSL frameworks, however, the low-quality predictions from the teacher model have seriously limited its performance. In this work, we propose a new Pseudo-Labeling framework for semi-supervised 3D object detection, by enhancing the teacher model to a proficient one with several necessary designs. First, to improve the recall of pseudo labels, a Spatialtemporal Ensemble (STE) module is proposed to generate sufficient seed boxes. Second, to improve the precision of recalled boxes, a Clusteringbased Box Voting (CBV) module is designed to get aggregated votes from the clustered seed boxes. This also eliminates the necessity of sophisticated thresholds to select pseudo labels. Furthermore, to reduce the negative influence of wrongly pseudo-labeled samples during the training, a soft supervision signal is proposed by considering Box-wise Contrastive Learning (BCL). The effectiveness of our model is verified on both ONCE and Waymo datasets. For example, on ONCE, our approach significantly improves the baseline by 9.51 mAP. Moreover, with half annotations, our model outperforms the oracle model with full annotations on Waymo.


page 1

page 2

page 3

page 4


Semi-supervised 3D Object Detection via Adaptive Pseudo-Labeling

3D object detection is an important task in computer vision. Most existi...

3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection

3D object detection is an important yet demanding task that heavily reli...

End-to-End Semi-Supervised Object Detection with Soft Teacher

This paper presents an end-to-end semi-supervised object detection appro...

W2N:Switching From Weak Supervision to Noisy Supervision for Object Detection

Weakly-supervised object detection (WSOD) aims to train an object detect...

NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection

The labeling cost of large number of bounding boxes is one of the main c...

An Empirical Study of Pseudo-Labeling for Image-based 3D Object Detection

Image-based 3D detection is an indispensable component of the perception...

Multi-Class 3D Object Detection with Single-Class Supervision

While multi-class 3D detectors are needed in many robotics applications,...

Please sign up or login with your details

Forgot password? Click here to reset