# Adaptive Margin Contrastive Learning for Ambiguity-aware 3D Semantic Segmentation

arXiv: https://arxiv.org/abs/2502.04111 · HTML: https://mlsanity.com/paper/2502.04111/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 35 references that are in the map.
- First posted on arXiv 6 Feb 2025.

## Builds on (most cited first, 27 of 27)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds](https://mlsanity.com/paper/2103.14635/) (2021)
- [Fast Point Transformer](https://mlsanity.com/paper/2112.04702/) (2021)
- [PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks](https://mlsanity.com/paper/1912.03264/) (2019)
- [A Closer Look at Local Aggregation Operators in Point Cloud Analysis](https://mlsanity.com/paper/2007.01294/) (2020)
- [Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2110.08188/) (2021)
- [Boosting Few-Shot Learning With Adaptive Margin Loss](https://mlsanity.com/paper/2005.13826/) (2020)
- [JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds](https://mlsanity.com/paper/2007.06888/) (2020)
- [Contrastive Boundary Learning for Point Cloud Segmentation](https://mlsanity.com/paper/2203.05272/) (2022)
- [Meta Architecture for Point Cloud Analysis](https://mlsanity.com/paper/2211.14462/) (2022)
- [Towards Semi-Supervised Deep Facial Expression Recognition with An Adaptive Confidence Margin](https://mlsanity.com/paper/2203.12341/) (2022)
- [SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation](https://mlsanity.com/paper/2012.10217/) (2020)
- [GeoAuxNet: Towards Universal 3D Representation Learning for Multi-sensor Point Clouds](https://mlsanity.com/paper/2403.19220/) (2024)

## Built on by (most cited first, 4 of 4)

- [3DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentation](https://mlsanity.com/paper/2504.12599/) (2025)
- [Ambiguity-aware Point Cloud Segmentation by Adaptive Margin Contrastive Learning](https://mlsanity.com/paper/2507.06592/) (2025)
- [AdapToPASS: Ambiguity-aware Adaptive Spherical Transformer for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2608.29081/) (2026)
- [PointVDP: Learning View-Dependent Projection by Fireworks Rays for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2507.06618/) (2025)

## Abstract (arXiv)

In this paper, we propose an adaptive margin contrastive learning method for 3D point cloud semantic segmentation, namely AMContrast3D. Most existing methods use equally penalized objectives, which ignore per-point ambiguities and less discriminated features stemming from transition regions. However, as highly ambiguous points may be indistinguishable even for humans, their manually annotated labels are less reliable, and hard constraints over these points would lead to sub-optimal models. To address this, we design adaptive objectives for individual points based on their ambiguity levels, aiming to ensure the correctness of low-ambiguity points while allowing mistakes for high-ambiguity points. Specifically, we first estimate ambiguities based on position embeddings. Then, we develop a margin generator to shift decision boundaries for contrastive feature embeddings, so margins are narrowed due to increasing ambiguities with even negative margins for extremely high-ambiguity points. Experimental results on large-scale datasets, S3DIS and ScanNet, demonstrate that our method outperforms state-of-the-art methods.