Dual Sparse Aggregation Transformer for Multispectral Object Detection
双稀疏聚合Transformer用于多光谱目标检测
机构 * Northwestern Polytechnical University(西北工业大学) ; School of Computer Science, Northwestern Polytechnical University(西北工业大学计算机学院) ; School of Cybersecurity, Northwestern Polytechnical University(西北工业大学网络空间安全学院) ; Shaanxi Provincial Key Laboratory of Speech and Image Information Processing(陕西省语音与图像信息处理重点实验室) ; National Engineering Laboratory for Integrated Aerospace-Ground-Ocean Big Data Application Technology(空天地海一体化大数据应用技术国家工程实验室)
专题命中 多模态训练与对齐 :multimodal(abstract);cross-modal(abstract);分类 cs.CV
AI总结 提出双稀疏聚合Transformer(DSAFormer),通过空间和通道稀疏注意力机制减少冗余交互,并引入可学习加法融合模块增强多模态特征融合,在四个数据集上达到最优检测性能。