基于对比学习的声源定位引导视听分割模型

黄文湖,赵邢,谢亮,梁浩然,梁荣华

Contrastive learning-based sound source localization-guided audio-visual segmentation model

Wenhu HUANG,Xing ZHAO,Liang XIE,Haoran LIANG,Ronghua LIANG

表 11 可学习查询对模型性能的影响

Tab.11 Impact of learnable queries on model performance

可学习嵌入 S4 MS3 $ {M_{\text{J}}} $/% $ {M_{\text{F}}} $/% $ {M_{\text{J}}} $/% $ {M_{\text{F}}} $/% 不添加 77.43 87.3 57.47 68.0 添加 78.68 88.0 59.50 69.8