Biologically-Inspired Evolutionary Domain Symbiosis for Few-shot and Zero-shot Point Cloud Semantic Segmentation

Few-shot and zero-shot point cloud semantic segmentation aim to accurately segment novel categories using limited or no labeled samples, respectively. However, existing methods face significant challenges including domain shifts between support and query sets and the inability to handle both few-shot and zero-shot scenarios within a unified framework. To address these issues, we propose a biologically-inspired Evolutionary Domain Symbiosis Network EDS-Net for unified few-shot and zero-shot point cloud semantic segmentation. Specifically, inspired by natural symbiotic evolution, we propose a Symbiotic Evolution Module (SEM) that models co-adaptation between support and query features through self-correlation and cross-correlation mechanisms. Second, motivated by genetic crossover mechanisms, we introduce a Vision-Semantic Bridging Module (VSBM) that treats visual prototypes and semantic prototypes as two “parent” individuals, creating fused offspring prototypes through adaptive crossover operations and mutation strategies for zero-shot scenarios. Third, we develop a multi-generational evolutionary optimization framework employing an adaptive gating network to learn optimal fusion weights across different evolutionary stages. Extensive experiments demonstrate that EDS-Net with biological interpretability achieves state-of-the-art performance on both few-shot and zero-shot settings.

Authors

• Changshuo Wang Nanyang Technological University, Singapore
• Zhijian Hu
• Xiang Fang Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology Key Laboratory of Data Protection and Intelligent Management (Sichuan University), Ministry of Education
• Zai Yang Yu Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China； University of Chinese Academy of Sciences, Beijing, China
• Yibin Wu Institute of Geodesy and Geoinformation, University of Bonn, Bonn, Germany
• Mingkun Xu Guangdong Institute of Intelligence Science and Technology Center for Brain Inspired Computing Research (CBICR), Department of Precision Instrument, Tsinghua University
• Yusong Wang Guangdong Institute of Intelligence Science and Technology Department of Information and Communications Engineering, Tokyo Institute of Technology
• Xingyu Gao Chinese Academy of Sciences and Nanyang Technological University
• Prayag Tiwari Halmstad University

Keywords

No keywords are indexed for this paper.