ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection

by   Jihan Yang, et al.
The University of Hong Kong

In this paper, we present a self-training method, named ST3D++, with a holistic pseudo label denoising pipeline for unsupervised domain adaptation on 3D object detection. ST3D++ aims at reducing noise in pseudo label generation as well as alleviating the negative impacts of noisy pseudo labels on model training. First, ST3D++ pre-trains the 3D object detector on the labeled source domain with random object scaling (ROS) which is designed to reduce target domain pseudo label noise arising from object scale bias of the source domain. Then, the detector is progressively improved through alternating between generating pseudo labels and training the object detector with pseudo-labeled target domain data. Here, we equip the pseudo label generation process with a hybrid quality-aware triplet memory to improve the quality and stability of generated pseudo labels. Meanwhile, in the model training stage, we propose a source data assisted training strategy and a curriculum data augmentation policy to effectively rectify noisy gradient directions and avoid model over-fitting to noisy pseudo labeled data. These specific designs enable the detector to be trained on meticulously refined pseudo labeled target data with denoised training signals, and thus effectively facilitate adapting an object detector to a target domain without requiring annotations. Finally, our method is assessed on four 3D benchmark datasets (i.e., Waymo, KITTI, Lyft, and nuScenes) for three common categories (i.e., car, pedestrian and bicycle). ST3D++ achieves state-of-the-art performance on all evaluated settings, outperforming the corresponding baseline by a large margin (e.g., 9.6 38.16 surpasses the fully supervised oracle results on the KITTI 3D object detection benchmark with target prior. Code will be available.


page 4

page 5


ST3D: Self-training for Unsupervised Domain Adaptation on 3D ObjectDetection

We present a new domain adaptive self-training pipeline, named ST3D, for...

A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data

Unsupervised domain adaptation (UDA) assumes that source and target doma...

Unsupervised Domain Adaptation for Multispectral Pedestrian Detection

Multimodal information (e.g., visible and thermal) can generate robust p...

MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection

Existing cross-domain keypoint detection methods always require accessin...

Robust Target Training for Multi-Source Domain Adaptation

Given multiple labeled source domains and a single target domain, most e...

CLIP-VG: Self-paced Curriculum Adapting of CLIP via Exploiting Pseudo-Language Labels for Visual Grounding

Visual Grounding (VG) refers to locating a region described by expressio...

Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection

3D object detection networks tend to be biased towards the data they are...

Please sign up or login with your details

Forgot password? Click here to reset