DeCUR decoupling common & unique representations for multimodal self-supervision

• 论文名称: DeCUR: decoupling common & unique representations for multimodal self-supervision
• Link: https://arxiv.org/abs/2309.05300
• Published in: Arxiv 2023
• Type: Pretrain
• Code/Project: https://github.com/zhu-xlab/DeCUR
• 备注: 多模态，对比学习
• Backbone: Resnet
• Backbone 1: ResNet50
• 下游任务: Classification, Semantic Segmentation
• 下游任务 1: classification and segmentation
• Short Summary: 在不同模态间分离了通用和独特的表示，增强了模态内和跨模态的学习。