Learnability-Driven Submodular Optimization for Active Roadside 3D Detection

• URL: http://arxiv.org/abs/2601.01695v1
• Date: Sun, 04 Jan 2026 23:59:06 GMT
• Title: Learnability-Driven Submodular Optimization for Active Roadside 3D Detection
• Authors: Ruiyu Mao, Baoming Zhang, Nicholas Ruozzi, Yunhui Guo,
• Abstract summary: This work focuses on active learning for roadside monocular 3D object detection.<n>We propose a learnability-driven framework that selects scenes which are both informative and reliably labelable.<n>Experiments demonstrate that our method, LH3D, achieves 86.06%, 67.32%, and 78.67% of full-performance for vehicles, pedestrians, and cyclists respectively.
• Score: 24.30599734067415
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Roadside perception datasets are typically constructed via cooperative labeling between synchronized vehicle and roadside frame pairs. However, real deployment often requires annotation of roadside-only data due to hardware and privacy constraints. Even human experts struggle to produce accurate labels without vehicle-side data (image, LIDAR), which not only increases annotation difficulty and cost, but also reveals a fundamental learnability problem: many roadside-only scenes contain distant, blurred, or occluded objects whose 3D properties are ambiguous from a single view and can only be reliably annotated by cross-checking paired vehicle--roadside frames. We refer to such cases as inherently ambiguous samples. To reduce wasted annotation effort on inherently ambiguous samples while still obtaining high-performing models, we turn to active learning. This work focuses on active learning for roadside monocular 3D object detection and proposes a learnability-driven framework that selects scenes which are both informative and reliably labelable, suppressing inherently ambiguous samples while ensuring coverage. Experiments demonstrate that our method, LH3D, achieves 86.06%, 67.32%, and 78.67% of full-performance for vehicles, pedestrians, and cyclists respectively, using only 25% of the annotation budget on DAIR-V2X-I, significantly outperforming uncertainty-based baselines. This confirms that learnability, not uncertainty, matters for roadside 3D perception.

Related papers

• PLOT: Pseudo-Labeling via Video Object Tracking for Scalable Monocular 3D Object Detection [35.524943073010675]
  Monocular 3D object detection (M3OD) has long faced challenges due to data scarcity caused by high annotation costs and inherent 2D-to-3D ambiguity.<n>We propose a novel pseudo-labeling framework that uses only video data and is more robust to occlusion, without requiring a multi-view setup, additional sensors, camera poses, or domain-specific training.
  arXiv  Detail & Related papers  (2025-07-03T07:46:39Z)
• ToosiCubix: Monocular 3D Cuboid Labeling via Vehicle Part Annotations [0.40964539027092906]
  Toosiix is a simple yet powerful approach for annotating ground-truth cuboids using only monocular images and camera parameters.<n>Our method requires only about 10 user clicks per vehicle, making it highly practical for adding 3D annotations to existing datasets.<n>We validate our annotations against the KITTI and Cityscapes3D datasets, demonstrating that our method offers a cost-effective and scalable solution.
  arXiv  Detail & Related papers  (2025-06-26T15:09:33Z)
• Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving [14.403130104985557]
  This paper presents a novel dataset for anomaly segmentation in driving scenarios.<n>It is the first publicly available dataset focused on road anomaly segmentation with dense 3D semantic labeling.<n>Our dataset and evaluation code will be openly available, facilitating the testing and performance comparison of different approaches.
  arXiv  Detail & Related papers  (2025-05-04T15:15:35Z)
• Uncertainty Estimation for 3D Object Detection via Evidential Learning [63.61283174146648]
  We introduce a framework for quantifying uncertainty in 3D object detection by leveraging an evidential learning loss on Bird's Eye View representations in the 3D detector. We demonstrate both the efficacy and importance of these uncertainty estimates on identifying out-of-distribution scenes, poorly localized objects, and missing (false negative) detections.
  arXiv  Detail & Related papers  (2024-10-31T13:13:32Z)
• View-to-Label: Multi-View Consistency for Self-Supervised 3D Object Detection [46.077668660248534]
  We propose a novel approach to self-supervise 3D object detection purely from RGB sequences alone. Our experiments on KITTI 3D dataset demonstrate performance on par with state-of-the-art self-supervised methods.
  arXiv  Detail & Related papers  (2023-05-29T09:30:39Z)
• Unsupervised Adaptation from Repeated Traversals for Autonomous Driving [54.59577283226982]
  Self-driving cars must generalize to the end-user's environment to operate reliably. One potential solution is to leverage unlabeled data collected from the end-users' environments. There is no reliable signal in the target domain to supervise the adaptation process. We show that this simple additional assumption is sufficient to obtain a potent signal that allows us to perform iterative self-training of 3D object detectors on the target domain.
  arXiv  Detail & Related papers  (2023-03-27T15:07:55Z)
• Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency [78.76508318592552]
  Monocular 3D object detection has become a mainstream approach in automatic driving for its easy application. Most current methods still rely on 3D point cloud data for labeling the ground truths used in the training phase. We propose a new weakly supervised monocular 3D objection detection method, which can train the model with only 2D labels marked on images.
  arXiv  Detail & Related papers  (2023-03-15T15:14:00Z)
• Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection [58.81316192862618]
  Two critical sensors for 3D perception in autonomous driving are the camera and the LiDAR. fusing these two modalities can significantly boost the performance of 3D perception models. We benchmark the state-of-the-art fusion methods for the first time.
  arXiv  Detail & Related papers  (2022-05-30T09:35:37Z)
• Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Driving [45.405303803618]
  We investigate diversity-based active learning (AL) as a potential solution to alleviate the annotation burden. We propose a novel acquisition function that enforces spatial and temporal diversity in the selected samples. We demonstrate the effectiveness of the proposed method on the nuScenes dataset and show that it outperforms existing AL strategies significantly.
  arXiv  Detail & Related papers  (2022-05-16T14:21:30Z)
• Road Curb Detection and Localization with Monocular Forward-view Vehicle Camera [74.45649274085447]
  We propose a robust method for estimating road curb 3D parameters using a calibrated monocular camera equipped with a fisheye lens. Our approach is able to estimate the vehicle to curb distance in real time with mean accuracy of more than 90%.
  arXiv  Detail & Related papers  (2020-02-28T00:24:18Z)

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.