Confidence-Aware Superpixel Self-Supervised Learning for Cross-Modal Point Cloud Recognition

The high cost of 3-D annotation severely limits the availability of high-quality labeled data, posing a critical bottleneck to point cloud recognition tasks. In contrast, acquiring and annotating natural images is far more cost-effective, making 2-D image-based methods more accessible. With the rise of large-scale pretrained 2-D feature extraction models, which have demonstrated remarkable embedding capabilities across diverse domains, an opportunity emerges to leverage them for 3-D point cloud tasks. By transferring knowledge from well-established 2-D models, reliance on 3-D annotation can be significantly reduced while improving feature extraction efficiency. However, adapting these 2-D models, originally trained on natural images, to remote sensing data introduces several challenges. In particularly, the generalization ability of 2-D models is limited, and widely used point-pixel constraint methods suffer from high computational complexity and low error tolerance. To address these issues, this letter proposes the confidence-aware superpixel self-supervised learning method (CS-SSP). By incorporating confidence estimation, CS-SSP enhances the reliability of cross-domain feature embeddings, ensuring accurate feature transfer from natural images to remote sensing data. Additionally, a superpixel-based constraint is introduced to reduce computational complexity. Moreover, CS-SSP employs a coarse-to-fine training strategy, progressively refining constraints to mitigate training difficulties. The experiments demonstrate that CS-SSP outperforms baseline methods across all metrics. Notably, when fine-tuning with extremely limited labeled samples, CS-SSP achieves the state-of-the-art (SOTA) accuracy across all key metrics, highlighting its strong advantage in low-data scenarios.