Abstract
Long-tailed 3D object detection is treated as a class-frequency problem, but LiDAR supervision quality depends on object observability: similar frequencies can hide different geometric evidence. We introduce Geometry-Augmented Exponentially Weighted Instance-Aware Repeat Factor Sampling (GA-EIRFS), a detector-agnostic method that modulates a frequency-based repeat factor with a fixed geometry score combining point count, surface-normal entropy, and surface coverage. GA-EIRFS changes only frame-sampling probabilities, leaving the detector and inference unchanged. On nuScenes it improves mean average precision (mAP) and the nuScenes detection score (NDS) in four converged experiments with CenterPoint and PointPillars over two seeds; for CenterPoint at seed 666, mAP rises from 0.552 to 0.563 and bicycle AP from 0.306 to 0.359. Per-class gains correlate with the class sampling-weight increase (Spearman rho=0.70, p=0.025) but not with geometry score alone (rho=0.32, p=0.37), so geometry amplifies frequency-driven need. KITTI results vary across seeds, most for the rarest class. Code: https://github.com/Multimodal-Sensing-Lab/GA-EIRFS.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Ahmed, T., Casado, C. Á., Castro, D. H., Sharifipour, S., Kumar, A., & López, M. B. (2026). GA-EIRFS: A Geometry-Augmented Repeat-Factor Sampling Method for Long-Tailed LiDAR 3D Object Detection. https://omanscience.com/en/articles/ga-eirfs-a-geometry-augmented-repeat-factor-sampling-method-for-long-tailed-lidar-3d-object-detection
MLA 9
Ahmed, Taufiq, et al. "GA-EIRFS: A Geometry-Augmented Repeat-Factor Sampling Method for Long-Tailed LiDAR 3D Object Detection." https://omanscience.com/en/articles/ga-eirfs-a-geometry-augmented-repeat-factor-sampling-method-for-long-tailed-lidar-3d-object-detection.
Chicago (author–date)
Ahmed, Taufiq, Constantino Álvarez Casado, Daniel Herrera Castro, Sasan Sharifipour, Abhishek Kumar, and Miguel Bordallo López. 2026. "GA-EIRFS: A Geometry-Augmented Repeat-Factor Sampling Method for Long-Tailed LiDAR 3D Object Detection." https://omanscience.com/en/articles/ga-eirfs-a-geometry-augmented-repeat-factor-sampling-method-for-long-tailed-lidar-3d-object-detection.
Harvard
Ahmed, T., Casado, C. Á., Castro, D. H., Sharifipour, S., Kumar, A. and López, M. B. (2026) 'GA-EIRFS: A Geometry-Augmented Repeat-Factor Sampling Method for Long-Tailed LiDAR 3D Object Detection', Available at: https://omanscience.com/en/articles/ga-eirfs-a-geometry-augmented-repeat-factor-sampling-method-for-long-tailed-lidar-3d-object-detection.
Vancouver
Ahmed T, Casado CÁ, Castro DH, Sharifipour S, Kumar A, López MB. GA-EIRFS: A Geometry-Augmented Repeat-Factor Sampling Method for Long-Tailed LiDAR 3D Object Detection. https://omanscience.com/en/articles/ga-eirfs-a-geometry-augmented-repeat-factor-sampling-method-for-long-tailed-lidar-3d-object-detection
IEEE
T. Ahmed, C. Á. Casado, D. H. Castro, S. Sharifipour, A. Kumar, and M. B. López, "GA-EIRFS: A Geometry-Augmented Repeat-Factor Sampling Method for Long-Tailed LiDAR 3D Object Detection," https://omanscience.com/en/articles/ga-eirfs-a-geometry-augmented-repeat-factor-sampling-method-for-long-tailed-lidar-3d-object-detection.