# Localization and Expansion: A Decoupled Framework for Point Cloud Few-shot Semantic Segmentation

arXiv: https://arxiv.org/abs/2408.13752 · HTML: https://mlsanity.com/paper/2408.13752/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 25 Aug 2024.

## Builds on (most cited first, 26 of 26)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [Meta-learning with differentiable closed-form solvers](https://mlsanity.com/paper/1805.08136/) (2018)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [CrossTransformers: spatially-aware few-shot transfer](https://mlsanity.com/paper/2007.11498/) (2020)
- [Stratified Transformer for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2203.14508/) (2022)
- [Meta-Learning Probabilistic Inference For Prediction](https://mlsanity.com/paper/1805.09921/) (2018)
- [Finding Task-Relevant Features for Few-Shot Learning by Category Traversal](https://mlsanity.com/paper/1905.11116/) (2019)
- [Infinite Mixture Prototypes for Few-Shot Learning](https://mlsanity.com/paper/1902.04552/) (2019)
- [Self-Support Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2207.11549/) (2022)
- [Recurrent Slice Networks for 3D Segmentation of Point Clouds](https://mlsanity.com/paper/1802.04402/) (2018)
- [Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2006.12052/) (2020)
- [Memory Matching Networks for One-Shot Image Recognition](https://mlsanity.com/paper/1804.08281/) (2018)
- [Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancement](https://mlsanity.com/paper/2308.03177/) (2023)
- [Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network](https://mlsanity.com/paper/2303.15654/) (2023)
- [Image-to-Image Matching via Foundation Models: A New Perspective for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2404.00262/) (2024)
- [Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2311.17626/) (2023)
- [SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation](https://mlsanity.com/paper/2205.13490/) (2022)

## Built on by (most cited first, 6 of 6)

- [Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2410.22489/) (2024)
- [Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model](https://mlsanity.com/paper/2503.16282/) (2025)
- [Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentation](https://mlsanity.com/paper/2412.10339/) (2024)
- [Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective](https://mlsanity.com/paper/2512.06870/) (2025)
- [White Aggregation and Restoration for Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2509.13907/) (2025)
- [Adaptive Augmentation-Aware Latent Learning for Robust LiDAR Semantic Segmentation](https://mlsanity.com/paper/2603.01074/) (2026)

## Abstract (arXiv)

Point cloud few-shot semantic segmentation (PC-FSS) aims to segment targets of novel categories in a given query point cloud with only a few annotated support samples. The current top-performing prototypical learning methods employ prototypes originating from support samples to direct the classification of query points. However, the inherent fragility of point-level matching and the prevalent intra-class diversity pose great challenges to this cross-instance matching paradigm, leading to erroneous background activations or incomplete target excavation. In this work, we propose a simple yet effective framework in the spirit of Decoupled Localization and Expansion (DLE). The proposed DLE, including a structural localization module (SLM) and a self-expansion module (SEM), enjoys several merits. First, structural information is injected into the matching process through the agent-level correlation in SLM, and the confident target region can thus be precisely located. Second, more reliable intra-object similarity is harnessed in SEM to derive the complete target, and the conservative expansion strategy is introduced to reasonably constrain the expansion. Extensive experiments on two challenging benchmarks under different settings demonstrate that DLE outperforms previous state-of-the-art approaches by large margins.