Paper Info
Title
Hierarchical Memory Learning for Fine-Grained Scene Graph Generation.
Abstract
Regarding Scene Graph Generation (SGG), coarse and fine predicates mix in the dataset due to the crowd-sourced labeling, and the long-tail problem is also pronounced. Given this tricky situation, many existing SGG methods treat the predicates equally and learn the model under the supervision of mixed-granularity predicates in one stage, leading to relatively coarse predictions. In order to alleviate the impact of the suboptimum mixed-granularity annotation and long-tail effect problems, this paper proposes a novel Hierarchical Memory Learning (HML) framework to learn the model from simple to complex, which is similar to the human beings’ hierarchical memory learning process. After the autonomous partition of coarse and fine predicates, the model is first trained on the coarse predicates and then learns the fine predicates. In order to realize this hierarchical learning pattern, this paper, for the first time, formulates the HML framework using the new Concept Reconstruction (CR) and Model Reconstruction (MR) constraints. It is worth noticing that the HML framework can be taken as one general optimization strategy to improve various SGG models, and significant improvement can be achieved on the SGG benchmark.
Year
DOI
Venue
2022
10.1007/978-3-031-19812-0_16
European Conference on Computer Vision
Keywords
DocType
Citations 
Scene graph generation,Mixed-granularity annotation,Hierarchical memory learning
Conference
0
PageRank 
References 
Authors
0.34
0
7
Name
Order
Citations
PageRank
Youming Deng100.34
Yansheng Li213614.02
Yongjun Zhang316433.87
Xiang Xiang400.34
Jian Wang500.34
Jingdong Chen61460128.79
Jiayi Ma7130265.86