Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: An, Zhaochong, Sun, Guolei, Liu, Yun, Li, Runjia, Wu, Min, Cheng, Ming-Ming, Konukoglu, Ender, Belongie, Serge
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913707006623744
author An, Zhaochong
Sun, Guolei
Liu, Yun
Li, Runjia
Wu, Min
Cheng, Ming-Ming
Konukoglu, Ender
Belongie, Serge
author_facet An, Zhaochong
Sun, Guolei
Liu, Yun
Li, Runjia
Wu, Min
Cheng, Ming-Ming
Konukoglu, Ender
Belongie, Serge
contents Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples. While existing FS-PCS methods have shown promise, they primarily focus on unimodal point cloud inputs, overlooking the potential benefits of leveraging multimodal information. In this paper, we address this gap by introducing a multimodal FS-PCS setup, utilizing textual labels and the potentially available 2D image modality. Under this easy-to-achieve setup, we present the MultiModal Few-Shot SegNet (MM-FSS), a model effectively harnessing complementary information from multiple modalities. MM-FSS employs a shared backbone with two heads to extract intermodal and unimodal visual features, and a pretrained text encoder to generate text embeddings. To fully exploit the multimodal information, we propose a Multimodal Correlation Fusion (MCF) module to generate multimodal correlations, and a Multimodal Semantic Fusion (MSF) module to refine the correlations using text-aware semantic guidance. Additionally, we propose a simple yet effective Test-time Adaptive Cross-modal Calibration (TACC) technique to mitigate training bias, further improving generalization. Experimental results on S3DIS and ScanNet datasets demonstrate significant performance improvements achieved by our method. The efficacy of our approach indicates the benefits of leveraging commonly-ignored free modalities for FS-PCS, providing valuable insights for future research. The code is available at https://github.com/ZhaochongAn/Multimodality-3D-Few-Shot
format Preprint
id arxiv_https___arxiv_org_abs_2410_22489
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation
An, Zhaochong
Sun, Guolei
Liu, Yun
Li, Runjia
Wu, Min
Cheng, Ming-Ming
Konukoglu, Ender
Belongie, Serge
Computer Vision and Pattern Recognition
Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples. While existing FS-PCS methods have shown promise, they primarily focus on unimodal point cloud inputs, overlooking the potential benefits of leveraging multimodal information. In this paper, we address this gap by introducing a multimodal FS-PCS setup, utilizing textual labels and the potentially available 2D image modality. Under this easy-to-achieve setup, we present the MultiModal Few-Shot SegNet (MM-FSS), a model effectively harnessing complementary information from multiple modalities. MM-FSS employs a shared backbone with two heads to extract intermodal and unimodal visual features, and a pretrained text encoder to generate text embeddings. To fully exploit the multimodal information, we propose a Multimodal Correlation Fusion (MCF) module to generate multimodal correlations, and a Multimodal Semantic Fusion (MSF) module to refine the correlations using text-aware semantic guidance. Additionally, we propose a simple yet effective Test-time Adaptive Cross-modal Calibration (TACC) technique to mitigate training bias, further improving generalization. Experimental results on S3DIS and ScanNet datasets demonstrate significant performance improvements achieved by our method. The efficacy of our approach indicates the benefits of leveraging commonly-ignored free modalities for FS-PCS, providing valuable insights for future research. The code is available at https://github.com/ZhaochongAn/Multimodality-3D-Few-Shot
title Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.22489