Various few-shot image classification methods indicate that transferring knowledge from other sources can improve the accuracy of the classification.However,most of these methods work with one single source or use onl...Various few-shot image classification methods indicate that transferring knowledge from other sources can improve the accuracy of the classification.However,most of these methods work with one single source or use only closely correlated knowledge sources.In this paper,we propose a novel weakly correlated knowledge integration(WCKI)framework to address these issues.More specifically,we propose a unified knowledge graph(UKG)to integrate knowledge transferred from different sources(i.e.,visual domain and textual domain).Moreover,a graph attention module is proposed to sample the subgraph from the UKG with low complexity.To avoid explicitly aligning the visual features to the potentially biased and weakly correlated knowledge space,we sample a task-specific subgraph from UKG and append it as latent variables.Our framework demonstrates significant improvements on multiple few-shot image classification datasets.展开更多
This article introduces briefly the development, the struCture and the running situation of a Jinlin flood disaster forecasting ES.In the field of meteorological phenomena,there is a lot of fuzzy phenomena,and concept...This article introduces briefly the development, the struCture and the running situation of a Jinlin flood disaster forecasting ES.In the field of meteorological phenomena,there is a lot of fuzzy phenomena,and concept posseSSing fuzziness. For this reason,we developed FBEST by fuzzy method.The application of FBEST will have great significance in preventing and decreasing disaster,protecting peoples lives and property.展开更多
基金supported by National Key Research and Development Program of China(No.2020AAA 09701)National Natural Science Foundation of China(Nos.62076024 and 62006018)。
文摘Various few-shot image classification methods indicate that transferring knowledge from other sources can improve the accuracy of the classification.However,most of these methods work with one single source or use only closely correlated knowledge sources.In this paper,we propose a novel weakly correlated knowledge integration(WCKI)framework to address these issues.More specifically,we propose a unified knowledge graph(UKG)to integrate knowledge transferred from different sources(i.e.,visual domain and textual domain).Moreover,a graph attention module is proposed to sample the subgraph from the UKG with low complexity.To avoid explicitly aligning the visual features to the potentially biased and weakly correlated knowledge space,we sample a task-specific subgraph from UKG and append it as latent variables.Our framework demonstrates significant improvements on multiple few-shot image classification datasets.
文摘This article introduces briefly the development, the struCture and the running situation of a Jinlin flood disaster forecasting ES.In the field of meteorological phenomena,there is a lot of fuzzy phenomena,and concept posseSSing fuzziness. For this reason,we developed FBEST by fuzzy method.The application of FBEST will have great significance in preventing and decreasing disaster,protecting peoples lives and property.
