# Few-shot 3D LiDAR Semantic Segmentation for Autonomous Driving

arXiv: https://arxiv.org/abs/2302.08785 · HTML: https://mlsanity.com/paper/2302.08785/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 17 Feb 2023.

## Builds on (most cited first, 23 of 23)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [One-Shot Learning for Semantic Segmentation](https://mlsanity.com/paper/1709.03410/) (2017)
- [SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving](https://mlsanity.com/paper/2003.03653/) (2020)
- [CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning](https://mlsanity.com/paper/1903.02351/) (2019)
- [Modeling the Background for Incremental Learning in Semantic Segmentation](https://mlsanity.com/paper/2002.00718/) (2020)
- [Prototype Mixture Models for Few-shot Semantic Segmentation](https://mlsanity.com/paper/2008.03898/) (2020)
- [Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning](https://mlsanity.com/paper/1909.13032/) (2019)
- [Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review](https://mlsanity.com/paper/2005.09830/) (2020)
- [Self-Guided and Cross-Guided Learning for Few-Shot Segmentation](https://mlsanity.com/paper/2103.16129/) (2021)
- [Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2006.12052/) (2020)
- [Generalized Few-shot Semantic Segmentation](https://mlsanity.com/paper/2010.05210/) (2020)
- [Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2110.11650/) (2021)
- [Are We Hungry for 3D LiDAR Data for Semantic Segmentation? A Survey and Experimental Study](https://mlsanity.com/paper/2006.04307/) (2020)
- [Compositional Prototype Network with Multi-view Comparision for Few-Shot Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2012.14255/) (2020)
- [Self-Regularized Prototypical Network for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2210.16829/) (2022)
- [RangeSeg: Range-Aware Real Time Segmentation of 3D LiDAR Point Clouds](https://mlsanity.com/paper/2205.01570/) (2022)
- [Generalized Few-Shot Semantic Segmentation: All You Need is Fine-Tuning](https://mlsanity.com/paper/2112.10982/) (2021)
- [Residual-driven Fuzzy C-Means Clustering for Image Segmentation](https://mlsanity.com/paper/2004.07160/) (2020)
- [G-image Segmentation: Similarity-preserving Fuzzy C-Means with Spatial Information Constraint in Wavelet Space](https://mlsanity.com/paper/2006.11510/) (2020)

## Built on by (most cited first, 3 of 3)

- [Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives](https://mlsanity.com/paper/2402.02968/) (2024)
- [Label-Efficient Semantic Segmentation of LiDAR Point Clouds in Adverse Weather Conditions](https://mlsanity.com/paper/2406.09906/) (2024)
- [TeFF: Tracking-enhanced Forgetting-free Few-shot 3D LiDAR Semantic Segmentation](https://mlsanity.com/paper/2408.15657/) (2024)

## Abstract (arXiv)

In autonomous driving, the novel objects and lack of annotations challenge the traditional 3D LiDAR semantic segmentation based on deep learning. Few-shot learning is a feasible way to solve these issues. However, currently few-shot semantic segmentation methods focus on camera data, and most of them only predict the novel classes without considering the base classes. This setting cannot be directly applied to autonomous driving due to safety concerns. Thus, we propose a few-shot 3D LiDAR semantic segmentation method that predicts both novel classes and base classes simultaneously. Our method tries to solve the background ambiguity problem in generalized few-shot semantic segmentation. We first review the original cross-entropy and knowledge distillation losses, then propose a new loss function that incorporates the background information to achieve 3D LiDAR few-shot semantic segmentation. Extensive experiments on SemanticKITTI demonstrate the effectiveness of our method.