SuppreSensing: Expert-Guided Feature Recalibration and Discrepancy Augmentation for Multimodal Object Detection
SuppreSensing:面向多模态目标检测的专家引导特征重校准与差异增强
机构 * Beijing University of Posts and Telecommunications(北京邮电大学)
专题命中 多模态评测 :multimodal(title,abstract);cross-modal(abstract);分类 cs.CV
AI总结 针对遥感多模态目标检测的语义异质性与模态噪声问题,本文提出SuppreSensing,通过EMFR模块、差异增强策略和ECFP模块实现最优性能,在多个数据集上达到SOTA并具备良好泛化性。
Comments 10 pages