Mind the Gap: Learning Modality-Agnostic Representations with a Cross-Modality UNet
Mind the Gap: Learning Modality-Agnostic Representations with a Cross-Modality UNet
机构 * Tianjin Key Laboratory of Intelligent Robotics, College of Artificial Intelligence, Nankai University, China(天津智能机器人重点实验室,人工智能学院,南开大学,中国) ; Engineering Research Center of Trusted Behavior Intelligence, Ministry of Education, Nankai University, China(可信行为智能工程研究中心,教育部,南开大学,中国) ; Department of Computer Science, Haifa University, Israel(计算机科学系,海法大学,以色列) ; VisionMetric Ltd, Canterbury, Kent, UK(VisionMetric Ltd,坎特伯雷,肯特,英国)
专题命中 红外-可见光融合 :infrared and visible(abstract,abstract_cn);分类 cs.CV
AI总结 本文提出了一种紧凑的编码器-解码器神经模块(cmUNet),通过跨模态转换和模态内重建,学习模态无关的表示,同时保留身份相关的信息。此外,作者提出了MarrNet,通过将cmUNet连接到标准特征提取网络,实现跨模态匹配,并在多个挑战性任务上验证了其优越性能。
Comments Published in IEEE Transactions on Image Processing. See full abstract in the PDF file
Journal ref n IEEE Transactions on Image Processing, vol. 33, pp. 655-670, 2024