Related papers: Self-Aware Adaptive Alignment: Enabling Accurate P…

Many existing autonomous driving paradigms involve a multi-stage discrete pipeline of tasks. To better predict the control signals and enhance user safety, an end-to-end approach that benefits from joint spatial-temporal feature learning is…

Collaborative perception among multiple connected and autonomous vehicles can greatly enhance perceptive capabilities by allowing vehicles to exchange supplementary information via communications. Despite advances in previous approaches,…

In recent years, object detection has shown impressive results using supervised deep learning, but it remains challenging in a cross-domain environment. The variations of illumination, style, scale, and appearance in different domains can…

Place recognition plays an essential role in the field of autonomous driving and robot navigation. Point cloud based methods mainly focus on extracting global descriptors from local features of point clouds. Despite having achieved…

In this study, we address a gap in existing unsupervised domain adaptation approaches on LiDAR-based 3D object detection, which have predominantly concentrated on adapting between established, high-density autonomous driving datasets. We…

We focus on bridging domain discrepancy in lane detection among different scenarios to greatly reduce extra annotation and re-training costs for autonomous driving. Critical factors hinder the performance improvement of cross-domain lane…

Collaborative perception has recently gained significant attention in autonomous driving, improving perception quality by enabling the exchange of additional information among vehicles. However, deploying collaborative perception systems…

Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. Unfortunately, it has received much less attention than supervised object detection. Models that try to address this task tend…

Accurate detection of objects in 3D point clouds is a key problem in autonomous driving systems. Collaborative perception can incorporate information from spatially diverse sensors and provide significant benefits for improving the…

Domain adaptation for semantic segmentation aims to improve the model performance in the presence of a distribution shift between source and target domain. Leveraging the supervision from auxiliary tasks~(such as depth estimation) has the…

We present a new semi-supervised domain adaptation framework that combines a novel auto-encoder-based domain adaptation model with a simultaneous learning scheme providing stable improvements over state-of-the-art domain adaptation models.…

While domain adaptation has been used to improve the performance of object detectors when the training and test data follow different distributions, previous work has mostly focused on two-stage detectors. This is because their use of…

A domain adaptive object detector aims to adapt itself to unseen domains that may contain variations of object appearance, viewpoints or backgrounds. Most existing methods adopt feature alignment either on the image level or instance level.…

Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored. In…

Adapting deep learning networks for point cloud data recognition in self-driving vehicles faces challenges due to the variability in datasets and sensor technologies, emphasizing the need for adaptive techniques to maintain accuracy across…

The rapid development of 3D object detection systems for self-driving cars has significantly improved accuracy. However, these systems struggle to generalize across diverse driving environments, which can lead to safety-critical failures in…

Object detection through either RGB images or the LiDAR point clouds has been extensively explored in autonomous driving. However, it remains challenging to make these two data sources complementary and beneficial to each other. In this…

LiDAR-based 3D detection has made great progress in recent years. However, the performance of 3D detectors is considerably limited when deployed in unseen environments, owing to the severe domain gap problem. Existing domain adaptive 3D…

Road safety mapping using satellite images is a cost-effective but a challenging problem for smart city planning. The scarcity of labeled data, misalignment and ambiguity makes it hard for supervised deep networks to learn efficient…

In this paper, we propose a self-supervised learningmethod for multi-object pose estimation. 3D object under-standing from 2D image is a challenging task that infers ad-ditional dimension from reduced-dimensional information.In particular,…