IEEE

Efficient Semantic Segmentation of Transmission Line Corridor Point Clouds via Transformer With Vector Aggregation

Abstract: Ensuring precise segmentation of point clouds is essential for intelligent inspection in transmission line corridors. The massive scale, unordered distribution, and complex structures of ...
IEEE

Cross-Modality Feature Aggregation for Cross-Domain Point Cloud Representation Learning

Abstract: Existing methods for learning 3D point cloud representation often use a single dataset-specific training and testing approach, leading to performance drops due to significant domain shifts ...
IEEE

Dual-Neighborhood Feature Aggregation Network for Point Cloud Semantic Segmentation

Abstract: Neighborhood construction plays a key role in point cloud processing. However, existing models only use a single neighborhood construction method to extract neighborhood features, which ...
IEEE

DCNet: Large-Scale Point Cloud Semantic Segmentation With Discriminative and Efficient Feature Aggregation

Abstract: The point cloud feature aggregation, which learns discriminative features from the disordered points, plays a key role for large-scale point cloud semantic segmentation. Most previous ...
IEEE

Neighborhood Spatial Aggregation MC Dropout for Efficient Uncertainty-Aware Semantic Segmentation in Point Clouds

Abstract: Uncertainty-aware semantic segmentation of the point clouds includes predictive uncertainty estimation and uncertainty-guided model optimization. One key challenge in the task is the ...
IEEE

Towards Privacy-Preserving and Error-Tolerant Wireless Federated Learning: Fixed-Point Model Aggregation with Differential Privacy Guarantees

Abstract: This paper presents a novel approach for wireless federated learning (WFL) that, for the first time, enables the aggregation of local models with mild to moderate errors under practical ...