# Input-Output Balanced Framework for Long-tailed LiDAR Semantic Segmentation

arXiv: https://arxiv.org/abs/2103.14269 · HTML: https://mlsanity.com/paper/2103.14269/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 26 Mar 2021.

## Builds on (most cited first, 22 of 22)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation](https://mlsanity.com/paper/2003.14032/) (2020)
- [SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud](https://mlsanity.com/paper/1710.07368/) (2017)
- [SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud](https://mlsanity.com/paper/1809.08495/) (2018)
- [SEGCloud: Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/1710.07563/) (2017)
- [OccuSeg: Occupancy-aware 3D Instance Segmentation](https://mlsanity.com/paper/2003.06537/) (2020)
- [Tangent Convolutions for Dense Prediction in 3D](https://mlsanity.com/paper/1807.02443/) (2018)
- [SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation](https://mlsanity.com/paper/2004.01803/) (2020)
- [Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax](https://mlsanity.com/paper/2006.10408/) (2020)
- [Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation](https://mlsanity.com/paper/2008.01550/) (2020)
- [LiDAR-based Panoptic Segmentation via Dynamic Shifting Network](https://mlsanity.com/paper/2011.11964/) (2020)
- [SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds](https://mlsanity.com/paper/2004.02774/) (2020)
- [Learning to Segment the Tail](https://mlsanity.com/paper/2004.00900/) (2020)
- [Factors in Finetuning Deep Model for object detection](https://mlsanity.com/paper/1601.05150/) (2016)
- [Reconfigurable Voxels: A New Representation for LiDAR-Based Point Clouds](https://mlsanity.com/paper/2004.02724/) (2020)

## Built on by (most cited first, 8 of 8)

- [FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detection](https://mlsanity.com/paper/2106.12449/) (2021)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception](https://mlsanity.com/paper/2109.05441/) (2021)
- [Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR](https://mlsanity.com/paper/2211.16951/) (2022)
- [Multi-Sem Fusion: Multimodal Semantic Fusion for 3D Object Detection](https://mlsanity.com/paper/2212.05265/) (2022)
- [Self-supervised Point Cloud Completion on Real Traffic Scenes via Scene-concerned Bottom-up Mechanism](https://mlsanity.com/paper/2203.10569/) (2022)
- [A Unified Framework for Human-centric Point Cloud Video Understanding](https://mlsanity.com/paper/2403.20031/) (2024)
- [HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes](https://mlsanity.com/paper/2403.02769/) (2024)
- [Distill, Diffuse, Segment: Unsupervised 3D Semantic Segmentation for Autonomous Driving Based on Multi-Level Distillation and Graph Diffusion](https://mlsanity.com/paper/2605.08293/) (2026)

## Abstract (arXiv)

A thorough and holistic scene understanding is crucial for autonomous vehicles, where LiDAR semantic segmentation plays an indispensable role. However, most existing methods focus on the network design while neglecting the inherent difficulty, imbalanced data distribution in the realistic dataset (also named long-tailed distribution), which narrows down the capability of state-of-the-art methods. In this paper, we propose an input-output balanced framework to handle the issue of long-tailed distribution. Specifically, for the input space, we synthesize these tailed instances from mesh models and well simulate the position and density distribution of LiDAR scan, which enhances the input data balance and improves the data diversity. For the output space, a multi-head block is proposed to group different categories based on their shapes and instance amounts, which alleviates the biased representation of dominating category during the feature learning. We evaluate the proposed model on two large-scale datasets, SemanticKITTI and nuScenes, where state-of-the-art results demonstrate its effectiveness. The proposed new modules can also be used as a plug-and-play, and we apply them on various backbones and datasets, showing its good generalization ability.