DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation

Changshuo Wang, Xiang Fang, Prayag Tiwari
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62845-62856, 2025.

Abstract

Few-shot point cloud semantic segmentation effectively addresses data scarcity by identifying unlabeled query samples through semantic prototypes generated from a small set of labeled support samples. However, pre-training-based methods suffer from domain shifts and increased training time. Additionally, existing methods using DGCNN as the backbone have limited geometric structure modeling capabilities and struggle to bridge the categorical information gap between query and support sets. To address these challenges, we propose DyPolySeg, a pre-training-free Dynamic Polynomial fitting network for few-shot point cloud semantic segmentation. Specifically, we design a unified Dynamic Polynomial Convolution (DyPolyConv) that extracts flat and detailed features of local geometry through Low-order Convolution (LoConv) and Dynamic High-order Convolution (DyHoConv), complemented by Mamba Block for capturing global context information. Furthermore, we propose a lightweight Prototype Completion Module (PCM) that reduces structural differences through self-enhancement and interactive enhancement between query and support sets. Experiments demonstrate that DyPolySeg achieves state-of-the-art performance on S3DIS and ScanNet datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-wang25aa, title = {{D}y{P}oly{S}eg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation}, author = {Wang, Changshuo and Fang, Xiang and Tiwari, Prayag}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {62845--62856}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/wang25aa/wang25aa.pdf}, url = {https://proceedings.mlr.press/v267/wang25aa.html}, abstract = {Few-shot point cloud semantic segmentation effectively addresses data scarcity by identifying unlabeled query samples through semantic prototypes generated from a small set of labeled support samples. However, pre-training-based methods suffer from domain shifts and increased training time. Additionally, existing methods using DGCNN as the backbone have limited geometric structure modeling capabilities and struggle to bridge the categorical information gap between query and support sets. To address these challenges, we propose DyPolySeg, a pre-training-free Dynamic Polynomial fitting network for few-shot point cloud semantic segmentation. Specifically, we design a unified Dynamic Polynomial Convolution (DyPolyConv) that extracts flat and detailed features of local geometry through Low-order Convolution (LoConv) and Dynamic High-order Convolution (DyHoConv), complemented by Mamba Block for capturing global context information. Furthermore, we propose a lightweight Prototype Completion Module (PCM) that reduces structural differences through self-enhancement and interactive enhancement between query and support sets. Experiments demonstrate that DyPolySeg achieves state-of-the-art performance on S3DIS and ScanNet datasets.} }
Endnote
%0 Conference Paper %T DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation %A Changshuo Wang %A Xiang Fang %A Prayag Tiwari %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-wang25aa %I PMLR %P 62845--62856 %U https://proceedings.mlr.press/v267/wang25aa.html %V 267 %X Few-shot point cloud semantic segmentation effectively addresses data scarcity by identifying unlabeled query samples through semantic prototypes generated from a small set of labeled support samples. However, pre-training-based methods suffer from domain shifts and increased training time. Additionally, existing methods using DGCNN as the backbone have limited geometric structure modeling capabilities and struggle to bridge the categorical information gap between query and support sets. To address these challenges, we propose DyPolySeg, a pre-training-free Dynamic Polynomial fitting network for few-shot point cloud semantic segmentation. Specifically, we design a unified Dynamic Polynomial Convolution (DyPolyConv) that extracts flat and detailed features of local geometry through Low-order Convolution (LoConv) and Dynamic High-order Convolution (DyHoConv), complemented by Mamba Block for capturing global context information. Furthermore, we propose a lightweight Prototype Completion Module (PCM) that reduces structural differences through self-enhancement and interactive enhancement between query and support sets. Experiments demonstrate that DyPolySeg achieves state-of-the-art performance on S3DIS and ScanNet datasets.
APA
Wang, C., Fang, X. & Tiwari, P.. (2025). DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:62845-62856 Available from https://proceedings.mlr.press/v267/wang25aa.html.

Related Material