Learning a Semantic Calibration Network for Open-Vocabulary Semantic Segmentation
学习语义校准网络用于开放词汇语义分割
机构 * University of Science and Technology of China(中国科学技术大学) ; Tsinghua University(清华大学) ; University of California, Berkeley(加州大学伯克利分校)
AI总结 提出语义校准网络(SCN),通过类消歧和logits融合模块显式建模类间语义相关性,在保持CLIP泛化能力的同时提升分割性能。
Comments Paper accepted by 11th International Conference on Intelligent Computing and Signal Processing (ICSP 2026)