# Long-Tailed 3D Detection via Multi-Modal Fusion

arXiv: https://arxiv.org/abs/2312.10986 · HTML: https://mlsanity.com/paper/2312.10986/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 75 of its 116 references that are in the map.
- First posted on arXiv 18 Dec 2023.

## Builds on (most cited first, 30 of 75)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [Argoverse: 3D Tracking and Forecasting with Rich Maps](https://mlsanity.com/paper/1911.02620/) (2019)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)

## Built on by (most cited first, 10 of 10)

- [Better Call SAL: Towards Learning to Segment Anything in Lidar](https://mlsanity.com/paper/2403.13129/) (2024)
- [Revisiting Few-Shot Object Detection with Vision-Language Models](https://mlsanity.com/paper/2312.14494/) (2023)
- [I Can't Believe It's Not Scene Flow!](https://mlsanity.com/paper/2403.04739/) (2024)
- [Roadside Monocular 3D Detection Prompted by 2D Detection](https://mlsanity.com/paper/2404.01064/) (2024)
- [DGFusion: Dual-guided Fusion for Robust Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2511.10035/) (2025)
- [FOMO-3D: Using Vision Foundation Models for Long-Tailed 3D Object Detection](https://mlsanity.com/paper/2603.08611/) (2026)
- [SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection](https://mlsanity.com/paper/2604.18476/) (2026)
- [AutoExpert: Automating 3D LiDAR Annotation from Expert-Crafted Guidelines](https://mlsanity.com/paper/2506.02914/) (2025)
- [OV3D-Bench: A Diagnostic Benchmark for Open-Vocabulary Monocular 3D Detection](https://mlsanity.com/paper/2608.17110/) (2026)
- [GA-EIRFS: A Geometry-Augmented Repeat-Factor Sampling Method for Long-Tailed LiDAR 3D Object Detection](https://mlsanity.com/paper/2609.38116/) (2026)

## Abstract (arXiv)

Contemporary autonomous vehicle (AV) benchmarks have significantly advanced multimodal (LiDAR+RGB) 3D detection. However, despite the naturally long-tailed distribution of object classes, existing benchmarking protocols primarily focus on frequent categories (e.g., pedestrian and car), largely overlooking rare but safety-critical classes such as stroller and emergency vehicle. In practice, reliable detection of both common and rare classes is essential for safe autonomous driving. We formalize this problem as Long-Tailed 3D Detection (LT3D), where evaluation encompasses all annotated classes, including rare ones. To address LT3D, we introduce hierarchical losses that promote feature sharing across classes, diagnostic metrics that assign partial credit to semantically reasonable mistakes with respect to the semantic hierarchy (e.g., confusing a child with an adult), and a multimodal late-fusion (MMLF) framework to fuse detections. In particular, we show that rare-class accuracy benefits substantially from MMLF of independently trained uni-modal LiDAR and RGB detectors. Because of the modular design, unlike prevailing end-to-end trained multi-modal detectors that require paired LiDAR-RGB data, MMLF enables the use of advanced unimodal detectors that are trained on large-scale uni-modal datasets with sufficient data for rare classes. Lastly, we examine three fundamental design choices in MMLF, including the RGB detector representation (2D vs. 3D), cross-modal association (3D vs. image plane), and fusion strategy. We find that 2D RGB detectors recognize rare classes more reliably than 3D RGB detectors, image-plane association is more robust to depth estimation errors, and probabilistic score-calibrated fusion consistently yields the best performance. Extensive experiments on nuScenes and Argoverse2 demonstrate substantial improvements of MMLF, establishing a new state of the art.