Related papers: Exploring Active 3D Object Detection from a Genera…
SSF3D modified the semi-supervised 3D object detection (SS3DOD) framework, which designed specifically for point cloud data. Leveraging the characteristics of non-coincidence and weak correlation of target objects in point cloud, we adopt a…
LiDAR datasets for autonomous driving exhibit biases in properties such as point cloud density, range, and object dimensions. As a result, object detection networks trained and evaluated in different environments often experience…
3D object trackers usually require training on large amounts of annotated data that is expensive and time-consuming to collect. Instead, we propose leveraging vast unlabeled datasets by self-supervised metric learning of 3D object trackers,…
Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are…
Point clouds are widely used representations of 3D data, but determining the visibility of points from a given viewpoint remains a challenging problem due to their sparse nature and lack of explicit connectivity. Traditional methods, such…
Safety of the Intended Functionality (SOTIF) addresses sensor performance limitations and deep learning-based object detection insufficiencies to ensure the intended functionality of Automated Driving Systems (ADS). This paper presents a…
Conventional active learning algorithms assume a single labeler that produces noiseless label at a given, fixed cost, and aim to achieve the best generalization performance for given classifier under a budget constraint. However, in many…
State-of-the-art 3D object detectors are often trained on massive labeled datasets. However, annotating 3D bounding boxes remains prohibitively expensive and time-consuming, particularly for LiDAR. Instead, recent works demonstrate that…
Inexpensive RGB-D cameras that give an RGB image together with depth data have become widely available. We use this data to build 3D point clouds of a full scene. In this paper, we address the task of labeling objects in this 3D point cloud…
This paper proposes a computationally efficient approach to detecting objects natively in 3D point clouds using convolutional neural networks (CNNs). In particular, this is achieved by leveraging a feature-centric voting scheme to implement…
LiDAR-based 3D object detectors often struggle to detect far-field objects due to the sparsity of point clouds at long ranges, which limits the availability of reliable geometric cues. To address this, prior approaches augment LiDAR data…
This paper aims at high-accuracy 3D object detection in autonomous driving scenario. We propose Multi-View 3D networks (MV3D), a sensory-fusion framework that takes both LIDAR point cloud and RGB images as input and predicts oriented 3D…
The vulnerability of 3D point cloud analysis to unpredictable rotations poses an open yet challenging problem: orientation-aware 3D domain generalization. Cross-domain robustness and adaptability of 3D representations are crucial but not…
In many real-world machine learning applications, unlabeled samples are easy to obtain, but it is expensive and/or time-consuming to label them. Active learning is a common approach for reducing this data labeling effort. It optimally…
Point cloud segmentation is a fundamental task in 3D. Despite recent progress on point cloud segmentation with the power of deep networks, current deep learning methods based on the clean label assumptions may fail with noisy labels. Yet,…
Active learning algorithms automatically identify the most informative samples from large amounts of unlabeled data and tremendously reduce human annotation effort in inducing a machine learning model. In a conventional active learning…
3D object detection from point clouds is crucial in safety-critical autonomous driving. Although many works have made great efforts and achieved significant progress on this task, most of them suffer from expensive annotation cost and poor…
Deep neural networks have reached high accuracy on object detection but their success hinges on large amounts of labeled data. To reduce the labels dependency, various active learning strategies have been proposed, typically based on the…
The cost of drawing object bounding boxes (i.e. labeling) for millions of images is prohibitively high. For instance, labeling pedestrians in a regular urban image could take 35 seconds on average. Active learning aims to reduce the cost of…
LiDAR point clouds can effectively depict the motion and posture of objects in three-dimensional space. Many studies accomplish the 3D object detection by voxelizing point clouds. However, in autonomous driving scenarios, the sparsity and…