A Category-Agnostic Hybrid Contrastive Learning Method for Few-Shot Point Cloud Object Detection
Xuejing Li*
The MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, 200240, China
* Corresponding Author: Xuejing Li. Email: 
Computers, Materials & Continua https://doi.org/10.32604/cmc.2025.062161
Received 11 December 2024; Accepted 25 February 2025; Published online 24 March 2025
Abstract
Few-shot point cloud 3D object detection (FS3D) aims to identify and locate objects of novel classes within point clouds using knowledge acquired from annotated base classes and a minimal number of samples from the novel classes. Due to imbalanced training data, existing FS3D methods based on fully supervised learning can lead to overfitting toward base classes, which impairs the network’s ability to generalize knowledge learned from base classes to novel classes and also prevents the network from extracting distinctive foreground and background representations for novel class objects. To address these issues, this thesis proposes a category-agnostic contrastive learning approach, enhancing the generalization and identification abilities for almost unseen categories through the construction of pseudo-labels and positive-negative sample pairs unrelated to specific classes. Firstly, this thesis designs a proposal-wise context contrastive module (CCM). By reducing the distance between foreground point features and increasing the distance between foreground and background point features within a region proposal, CCM aids the network in extracting more discriminative foreground and background feature representations without reliance on categorical annotations. Secondly, this thesis utilizes a geometric contrastive module (GCM), which enhances the network’s geometric perception capability by employing contrastive learning on the foreground point features associated with various basic geometric components, such as edges, corners, and surfaces, thereby enabling these geometric components to exhibit more distinguishable representations. This thesis also combines category-aware contrastive learning with former modules to maintain categorical distinctiveness. Extensive experimental results on FS-SUNRGBD and FS-ScanNet datasets demonstrate the effectiveness of this method with average precision exceeding the baseline by up to 8.
Keywords
Contrastive learning; few-shot learning; point cloud object detection
Open Access
Login
Register
Submit a Paper
Propose a Special lssue
Download PDF
Downloads
Citation Tools
