# Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud Segmentation

arXiv: https://arxiv.org/abs/2407.12489 · HTML: https://mlsanity.com/paper/2407.12489/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 41 references that are in the map.
- First posted on arXiv 17 Jul 2024.

## Builds on (most cited first, 28 of 28)

- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [Optimal Transport for Domain Adaptation](https://mlsanity.com/paper/1507.00504/) (2015)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation](https://mlsanity.com/paper/2003.14032/) (2020)
- [Learning to Discover Novel Visual Categories via Deep Transfer Clustering](https://mlsanity.com/paper/1908.09884/) (2019)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [Stratified Transformer for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2203.14508/) (2022)
- [A Unified Objective for Novel Class Discovery](https://mlsanity.com/paper/2108.08536/) (2021)
- [SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances](https://mlsanity.com/paper/2002.09147/) (2020)
- [Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review](https://mlsanity.com/paper/2005.09830/) (2020)
- [AutoNovel: Automatically Discovering and Learning Novel Visual Categories](https://mlsanity.com/paper/2106.15252/) (2021)
- [Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation](https://mlsanity.com/paper/2107.03358/) (2021)
- [PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery](https://mlsanity.com/paper/2212.05590/) (2022)
- [Unified Optimal Transport Framework for Universal Domain Adaptation](https://mlsanity.com/paper/2210.17067/) (2022)
- [GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2305.16404/) (2023)
- [Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Training](https://mlsanity.com/paper/2102.08622/) (2021)
- [Novel Class Discovery in Semantic Segmentation](https://mlsanity.com/paper/2112.01900/) (2021)
- [Class-relation Knowledge Distillation for Novel Class Discovery](https://mlsanity.com/paper/2307.09158/) (2023)
- [Novel Class Discovery for 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2303.11610/) (2023)
- [Novel Class Discovery for Long-tailed Recognition](https://mlsanity.com/paper/2308.02989/) (2023)
- [Incremental Class Discovery for Semantic Segmentation with RGBD Sensing](https://mlsanity.com/paper/1907.10008/) (2019)
- [P2OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering](https://mlsanity.com/paper/2401.09266/) (2024)

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

- [Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2410.22489/) (2024)
- [AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios](https://mlsanity.com/paper/2410.14379/) (2024)
- [LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2506.07857/) (2025)
- [Category Discovery: An Open-World Perspective](https://mlsanity.com/paper/2509.22542/) (2025)
- [RoBiS: Robust Binary Segmentation for High-Resolution Industrial Images](https://mlsanity.com/paper/2505.21152/) (2025)
- [Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning](https://mlsanity.com/paper/2510.13307/) (2025)
- [Composing Novel Classes: A Concept-Driven Approach to Generalized Category Discovery](https://mlsanity.com/paper/2410.13285/) (2024)
- [Freeze and Cluster: A Simple Baseline for Rehearsal-Free Continual Category Discovery](https://mlsanity.com/paper/2503.09106/) (2025)
- [Geometric-Aware Hypergraph Reasoning for Novel Class Discovery in Point Cloud Segmentation](https://mlsanity.com/paper/2606.07280/) (2026)
- [DP-BOA: Dirichlet-Process Birth-or-Assign for On-the-Fly Category Discovery](https://mlsanity.com/paper/2607.13504/) (2026)

## Abstract (arXiv)

We tackle the novel class discovery in point cloud segmentation, which discovers novel classes based on the semantic knowledge of seen classes. Existing work proposes an online point-wise clustering method with a simplified equal class-size constraint on the novel classes to avoid degenerate solutions. However, the inherent imbalanced distribution of novel classes in point clouds typically violates the equal class-size constraint. Moreover, point-wise clustering ignores the rich spatial context information of objects, which results in less expressive representation for semantic segmentation. To address the above challenges, we propose a novel self-labeling strategy that adaptively generates high-quality pseudo-labels for imbalanced classes during model training. In addition, we develop a dual-level representation that incorporates regional consistency into the point-level classifier learning, reducing noise in generated segmentation. Finally, we conduct extensive experiments on two widely used datasets, SemanticKITTI and SemanticPOSS, and the results show our method outperforms the state of the art by a large margin.