---
title: "Rethinking Multimodal Few-Shot 3D Point Cloud Segmentation: From Fused Refinement to Decoupled Arbitration"
authors:
  - "Wentao Bian"
  - "Fenglei Xu"
doi: "10.24963/ijcai.2026/103"
url: "https://ijcai.org/proceedings/2026/103"
pdf: "https://ijcai.org/proceedings/2026/0103.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "917-925"
track: "Main Track"
keywords:
  - "Computer Vision: 3D computer vision"
  - "Computer Vision: Vision, language and reasoning"
  - "Computer Vision: Segmentation, grouping and shape analysis"
  - "Computer Vision: Transfer, low-shot, semi- and un- supervised learning"
  - "Computer Vision: Multimodal learning"
---

# Rethinking Multimodal Few-Shot 3D Point Cloud Segmentation: From Fused Refinement to Decoupled Arbitration

Wentao Bian, Fenglei Xu

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 917-925. DOI: [10.24963/ijcai.2026/103](https://doi.org/10.24963/ijcai.2026/103)

## Abstract

In this paper, we revisit multimodal few-shot 3D point cloud semantic segmentation (FS-PCS), identifying a conflict in "Fuse-then-Refine" paradigms: the "Plasticity-Stability Dilemma." In addition, Contrastive Language-Image Pre-training (CLIP)'s inter-class confusion can result in semantic blindness. To address these issues, we present the Decoupled-experts Arbitration Few-Shot SegNet (DA-FSS), a model that effectively distinguishes between semantic and geometric paths and mutually regularizes their gradients to achieve better generalization. DA-FSS employs the same backbone and pre-trained text encoder as the baseline MultiModal Few-Shot SegNet (MM-FSS) to generate text embeddings, which can increase cost-free modalities' utilization rate and better leverage each modality's information space. To achieve this, we propose a Parallel Expert Refinement module to generate each modal correlation. We also propose a Stacked Arbitration Module (SAM) to perform convolutional fusion and arbitrate correlations for each modality pathway. The Parallel Experts decouple two paths: a Geometric Expert maintains plasticity, and a Semantic Expert ensures stability. They are coordinated via a Decoupled Alignment Module (DAM) that transfers knowledge without propagating confusion. Experiments on popular datasets (S3DIS, ScanNet) demonstrate the superiority of DA-FSS over MM-FSS. Meanwhile, geometric boundaries, completeness, and texture differentiation are all superior to the baseline. The code is available at: https://github.com/MoWenQAQ/DA-FSS/.