mlsanityData to 14 Oct 2026

GA-EIRFS: A Geometry-Augmented Repeat-Factor Sampling Method for Long-Tailed LiDAR 3D Object Detection

arXiv 2609.38116 ↗First posted 29 Sep 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 23 references that are in the map. First posted on arXiv 29 Sep 2026.

Builds on

16 of 23 references.

References · 16

  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  2. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  3. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  4. 2020Center-based 3D Object Detection and Trackingcited by 1,144
  5. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  6. 2019Deep Active Learning for Efficient Training of a LiDAR 3D Object Detectorcited by 45
  7. 2022Towards Long-Tailed 3D Detectioncited by 40
  8. 2022Class-Difficulty Based Methods for Long-Tailed Visual Recognitioncited by 23
  9. 2022Improving the Intra-class Long-tail in 3D Detection via Rare Example Miningcited by 19
  10. 2023Curricular Object Manipulation in LiDAR-based Object Detectioncited by 12
  11. 2023Long-Tailed 3D Detection via Multi-Modal Fusioncited by 10
  12. 2024Geometric Prior Guided Feature Representation Learning for Long-Tailed Classificationcited by 10
4 more
  1. 2023Instance-Aware Repeat Factor Sampling for Long-Tailed Object Detectioncited by 7
  2. 2023Generalized Few-Shot 3D Object Detection of LiDAR Point Cloud for Autonomous Drivingcited by 6
  3. 2022MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing for Active Annotation in Aerial Object Detectioncited by 3
  4. 2025Exponentially Weighted Instance-Aware Repeat Factor Sampling for Long-Tailed Object Detection Model Training in Unmanned Aerial Vehicles Surveillance Scenarioscited by 1

Built on by

Not cited yet.