Regarding extreme value theory,the unseen novelclasses in the openset recognition can be seen as the extremevalues of training classes.Following this idea,we introducethe margin and coverage distribution to model the ...Regarding extreme value theory,the unseen novelclasses in the openset recognition can be seen as the extremevalues of training classes.Following this idea,we introducethe margin and coverage distribution to model the trainingclasses.A novel visual-semantic embedding framework-extreme vocabulary learning(EVoL)is proposed;the EVoL embeds the visual features into semantic space in a probabilisticway.Notably,we adopt the vast open vocabulary in the semantic space to help further constraint the margin and coverage of training classes.The learned embedding can directlybe used to solve supervised learning,zero-shot learning,andopen set recognition simultaneously.Experiments on twobenchmark datasets demonstrate the effectiveness of the proposed framework against conventional ways.展开更多
文摘Regarding extreme value theory,the unseen novelclasses in the openset recognition can be seen as the extremevalues of training classes.Following this idea,we introducethe margin and coverage distribution to model the trainingclasses.A novel visual-semantic embedding framework-extreme vocabulary learning(EVoL)is proposed;the EVoL embeds the visual features into semantic space in a probabilisticway.Notably,we adopt the vast open vocabulary in the semantic space to help further constraint the margin and coverage of training classes.The learned embedding can directlybe used to solve supervised learning,zero-shot learning,andopen set recognition simultaneously.Experiments on twobenchmark datasets demonstrate the effectiveness of the proposed framework against conventional ways.
