Domain Generalization of 3D Object Detection by Density-Resampling
- URL: http://arxiv.org/abs/2311.10845v2
- Date: Wed, 28 Feb 2024 01:05:53 GMT
- Title: Domain Generalization of 3D Object Detection by Density-Resampling
- Authors: Shuangzhi Li, Lei Ma, and Xingyu Li
- Abstract summary: Point-cloud-based 3D object detection suffers from performance degradation when encountering data with novel domain gaps.
We propose an SDG method to improve the generalizability of 3D object detection to unseen target domains.
Our work introduces a novel data augmentation method and contributes a new multi-task learning strategy in the methodology.
- Score: 14.510085711178217
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Point-cloud-based 3D object detection suffers from performance degradation
when encountering data with novel domain gaps. To tackle it, the single-domain
generalization (SDG) aims to generalize the detection model trained in a
limited single source domain to perform robustly on unexplored domains. In this
paper, we propose an SDG method to improve the generalizability of 3D object
detection to unseen target domains. Unlike prior SDG works for 3D object
detection solely focusing on data augmentation, our work introduces a novel
data augmentation method and contributes a new multi-task learning strategy in
the methodology. Specifically, from the perspective of data augmentation, we
design a universal physical-aware density-based data augmentation (PDDA) method
to mitigate the performance loss stemming from diverse point densities. From
the learning methodology viewpoint, we develop a multi-task learning for 3D
object detection: during source training, besides the main standard detection
task, we leverage an auxiliary self-supervised 3D scene restoration task to
enhance the comprehension of the encoder on background and foreground details
for better recognition and detection of objects. Furthermore, based on the
auxiliary self-supervised task, we propose the first test-time adaptation
method for domain generalization of 3D object detection, which efficiently
adjusts the encoder's parameters to adapt to unseen target domains during
testing time, to further bridge domain gaps. Extensive cross-dataset
experiments covering "Car", "Pedestrian", and "Cyclist" detections, demonstrate
our method outperforms state-of-the-art SDG methods and even overpass
unsupervised domain adaptation methods under some circumstances.
Related papers
- Improving Generalization Ability for 3D Object Detection by Learning Sparsity-invariant Features [21.761631081209263]
We propose a method to improve the generalization ability for 3D object detection on a single domain.
To learn sparsity-invariant features from a single source domain, we selectively subsample the source data to a specific beam.
We also employ the teacher-student framework to align the Bird's Eye View features for different point clouds densities.
arXiv Detail & Related papers (2025-02-04T13:47:02Z) - Object Style Diffusion for Generalized Object Detection in Urban Scene [69.04189353993907]
We introduce a novel single-domain object detection generalization method, named GoDiff.
By integrating pseudo-target domain data with source domain data, we diversify the training dataset.
Experimental results demonstrate that our method not only enhances the generalization ability of existing detectors but also functions as a plug-and-play enhancement for other single-domain generalization methods.
arXiv Detail & Related papers (2024-12-18T13:03:00Z) - CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D
Object Detection [14.063365469339812]
LiDAR-based 3D Object Detection methods often do not generalize well to target domains outside the source (or training) data distribution.
We introduce a novel unsupervised domain adaptation (UDA) method, called CMDA, which leverages visual semantic cues from an image modality.
We also introduce a self-training-based learning strategy, wherein a model is adversarially trained to generate domain-invariant features.
arXiv Detail & Related papers (2024-03-06T14:12:38Z) - CLIP the Gap: A Single Domain Generalization Approach for Object
Detection [60.20931827772482]
Single Domain Generalization tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain.
We propose to leverage a pre-trained vision-language model to introduce semantic domain concepts via textual prompts.
We achieve this via a semantic augmentation strategy acting on the features extracted by the detector backbone, as well as a text-based classification loss.
arXiv Detail & Related papers (2023-01-13T12:01:18Z) - Towards Model Generalization for Monocular 3D Object Detection [57.25828870799331]
We present an effective unified camera-generalized paradigm (CGP) for Mono3D object detection.
We also propose the 2D-3D geometry-consistent object scaling strategy (GCOS) to bridge the gap via an instance-level augment.
Our method called DGMono3D achieves remarkable performance on all evaluated datasets and surpasses the SoTA unsupervised domain adaptation scheme.
arXiv Detail & Related papers (2022-05-23T23:05:07Z) - Unsupervised Domain Adaptation for Monocular 3D Object Detection via
Self-Training [57.25828870799331]
We propose STMono3D, a new self-teaching framework for unsupervised domain adaptation on Mono3D.
We develop a teacher-student paradigm to generate adaptive pseudo labels on the target domain.
STMono3D achieves remarkable performance on all evaluated datasets and even surpasses fully supervised results on the KITTI 3D object detection dataset.
arXiv Detail & Related papers (2022-04-25T12:23:07Z) - Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency [90.71745178767203]
Deep learning-based 3D object detection has achieved unprecedented success with the advent of large-scale autonomous driving datasets.
Existing 3D domain adaptive detection methods often assume prior access to the target domain annotations, which is rarely feasible in the real world.
We study a more realistic setting, unsupervised 3D domain adaptive detection, which only utilizes source domain annotations.
arXiv Detail & Related papers (2021-07-23T17:19:23Z) - ST3D: Self-training for Unsupervised Domain Adaptation on 3D
ObjectDetection [78.71826145162092]
We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds.
Our ST3D achieves state-of-the-art performance on all evaluated datasets and even surpasses fully supervised results on KITTI 3D object detection benchmark.
arXiv Detail & Related papers (2021-03-09T10:51:24Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.