4 papers
PointCSP: Cross-Sample Semantic Propagation and Stability Preservation in Self-Supervised Point Cloud Learning
Xinxing Yu, Ajian Liu, Sunyuan Qiang +5
Scene-level point cloud self-supervised learning (PC-SSL) has demonstrated potential in enhancing the generalization capability of 3D vision models. Despite the advances in the fie…
FeTT: Continual Class Incremental Learning via Feature Transformation Tuning
Sunyuan Qiang, Xuxin Lin, Yanyan Liang +2
Continual learning (CL) aims to extend deep models from static and enclosed environments to dynamic and complex scenarios, enabling systems to continuously acquire new knowledge of…
Open-Vocabulary Object Detection via Neighboring Region Attention Alignment
Sunyuan Qiang, Xianfei Li, Yanyan Liang +3
The nature of diversity in real-world environments necessitates neural network models to expand from closed category settings to accommodate novel emerging categories. In this pape…
Dynamic Feature Learning and Matching for Class-Incremental Learning
Sunyuan Qiang, Yanyan Liang, Jun Wan +1
Class-incremental learning (CIL) has emerged as a means to learn new classes incrementally without catastrophic forgetting of previous classes. Recently, CIL has undergone a paradi…