Few to Big: Prototype Expansion Network via Diffusion Learner for Point Cloud Few-shot Semantic Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Qianguang, Wang, Dongli, Zhou, Yan, Li, Jianxun, Irampa, Richard
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915496929001472
author Zhao, Qianguang
Wang, Dongli
Zhou, Yan
Li, Jianxun
Irampa, Richard
author_facet Zhao, Qianguang
Wang, Dongli
Zhou, Yan
Li, Jianxun
Irampa, Richard
contents Few-shot 3D point cloud semantic segmentation aims to segment novel categories using a minimal number of annotated support samples. While existing prototype-based methods have shown promise, they are constrained by two critical challenges: (1) Intra-class Diversity, where a prototype's limited representational capacity fails to cover a class's full variations, and (2) Inter-set Inconsistency, where prototypes derived from the support set are misaligned with the query feature space. Motivated by the powerful generative capability of diffusion model, we re-purpose its pre-trained conditional encoder to provide a novel source of generalizable features for expanding the prototype's representational range. Under this setup, we introduce the Prototype Expansion Network (PENet), a framework that constructs big-capacity prototypes from two complementary feature sources. PENet employs a dual-stream learner architecture: it retains a conventional fully supervised Intrinsic Learner (IL) to distill representative features, while introducing a novel Diffusion Learner (DL) to provide rich generalizable features. The resulting dual prototypes are then processed by a Prototype Assimilation Module (PAM), which adopts a novel push-pull cross-guidance attention block to iteratively align the prototypes with the query space. Furthermore, a Prototype Calibration Mechanism (PCM) regularizes the final big capacity prototype to prevent semantic drift. Extensive experiments on the S3DIS and ScanNet datasets demonstrate that PENet significantly outperforms state-of-the-art methods across various few-shot settings.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12878
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Few to Big: Prototype Expansion Network via Diffusion Learner for Point Cloud Few-shot Semantic Segmentation
Zhao, Qianguang
Wang, Dongli
Zhou, Yan
Li, Jianxun
Irampa, Richard
Computer Vision and Pattern Recognition
Few-shot 3D point cloud semantic segmentation aims to segment novel categories using a minimal number of annotated support samples. While existing prototype-based methods have shown promise, they are constrained by two critical challenges: (1) Intra-class Diversity, where a prototype's limited representational capacity fails to cover a class's full variations, and (2) Inter-set Inconsistency, where prototypes derived from the support set are misaligned with the query feature space. Motivated by the powerful generative capability of diffusion model, we re-purpose its pre-trained conditional encoder to provide a novel source of generalizable features for expanding the prototype's representational range. Under this setup, we introduce the Prototype Expansion Network (PENet), a framework that constructs big-capacity prototypes from two complementary feature sources. PENet employs a dual-stream learner architecture: it retains a conventional fully supervised Intrinsic Learner (IL) to distill representative features, while introducing a novel Diffusion Learner (DL) to provide rich generalizable features. The resulting dual prototypes are then processed by a Prototype Assimilation Module (PAM), which adopts a novel push-pull cross-guidance attention block to iteratively align the prototypes with the query space. Furthermore, a Prototype Calibration Mechanism (PCM) regularizes the final big capacity prototype to prevent semantic drift. Extensive experiments on the S3DIS and ScanNet datasets demonstrate that PENet significantly outperforms state-of-the-art methods across various few-shot settings.
title Few to Big: Prototype Expansion Network via Diffusion Learner for Point Cloud Few-shot Semantic Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.12878