Graph-based reasoning attention pooling with curriculum design for content-based image retrieval
作者：
Highlights：
• We propose a global single-pass method for content-based image retrieval.
• A novel trainable pooling method using graph-based reasoning and attention.
• Structural relations can effectively help emphasize the key features.
• Adopting curriculum design to modify the network training.
• The results shows the superiority over other methods on retrieval efficiency and accuracy on popular benchmarks.
摘要
Highlights•We propose a global single-pass method for content-based image retrieval.•A novel trainable pooling method using graph-based reasoning and attention.•Structural relations can effectively help emphasize the key features.•Adopting curriculum design to modify the network training.•The results shows the superiority over other methods on retrieval efficiency and accuracy on popular benchmarks.
论文关键词：Content-based image retrieval,Graph convolutional networks,Curriculum design
论文评审过程：Received 14 August 2021, Accepted 1 September 2021, Available online 7 September 2021, Version of Record 11 September 2021.
论文官网地址：https://doi.org/10.1016/j.imavis.2021.104289
