Cross-modal feature fusion and asymptotic decoding saliency target detection method and device

The invention discloses a saliency target detection method and device based on cross-modal feature fusion and asymptotic decoding. The method comprises the following steps of: extracting multi-level and multi-scale RGB (Red, Green, Blue) features and depth features from an image to be detected through a double-flow SwinTransform encoder; fusing the multi-level and multi-scale RGB features and the depth features through a cross-modal attention fusion module to obtain fused features; decoding high-level fusion features in the fusion features through a progressive fusion decoder, and fusing low-level features step by step in the decoding process; the problems that in the prior art, an additional feature enhancement or edge generation module needs to be added to achieve the most advanced effect, feature redundancy and computing resource waste are inevitably caused, and meanwhile further development of significance target detection model design is limited are solved. 本发明公开一种跨模态特征融合及渐近解码的显著性目标检测方法及装置。本发明通过双流SwinTra