# MILAN: Milli-Annotations for Lidar Semantic Segmentation

arXiv: https://arxiv.org/abs/2407.15797 · HTML: https://mlsanity.com/paper/2407.15797/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 43 of its 60 references that are in the map.
- First posted on arXiv 22 Jul 2024.

## Builds on (most cited first, 30 of 43)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving](https://mlsanity.com/paper/2003.03653/) (2020)
- [Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts](https://mlsanity.com/paper/2012.09165/) (2020)
- [CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP](https://mlsanity.com/paper/2301.04926/) (2023)
- [PLA: Language-Driven Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2211.16312/) (2022)
- [Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data](https://mlsanity.com/paper/2203.16258/) (2022)
- [LaserMix for Semi-Supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2207.00026/) (2022)
- [One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation](https://mlsanity.com/paper/2104.02246/) (2021)
- [Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2110.08188/) (2021)
- [Active Learning for Deep Object Detection via Probabilistic Modeling](https://mlsanity.com/paper/2103.16130/) (2021)
- [ALSO: Automotive Lidar Self-supervision by Occupancy estimation](https://mlsanity.com/paper/2212.05867/) (2022)
- [SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds](https://mlsanity.com/paper/2104.04891/) (2021)
- [Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders](https://mlsanity.com/paper/2206.09900/) (2022)
- [SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network](https://mlsanity.com/paper/2104.07861/) (2021)
- [Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2301.10100/) (2023)
- [ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2107.11769/) (2021)
- [Three Pillars improving Vision Foundation Model Distillation for Lidar](https://mlsanity.com/paper/2310.17504/) (2023)
- [LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds](https://mlsanity.com/paper/2210.08064/) (2022)

## Abstract (arXiv)

Annotating lidar point clouds for autonomous driving is a notoriously expensive and time-consuming task. In this work, we show that the quality of recent self-supervised lidar scan representations allows a great reduction of the annotation cost. Our method has two main steps. First, we show that self-supervised representations allow a simple and direct selection of highly informative lidar scans to annotate: training a network on these selected scans leads to much better results than a random selection of scans and, more interestingly, to results on par with selections made by SOTA active learning methods. In a second step, we leverage the same self-supervised representations to cluster points in our selected scans. Asking the annotator to classify each cluster, with a single click per cluster, then permits us to close the gap with fully-annotated training sets, while only requiring one thousandth of the point labels.