Open AccessDual semantic interdependencies attention network for person re‐identification
Author(s) -
Yang Shengrong,
Hu Haifeng,
Chen Dihu,
Su Tao
Publication year - 2020
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
ISSN - 1350-911X
DOI - 10.1049/el.2020.1786
Subject(s) - interdependence , computer science , dimension (graph theory) , discriminative model , semantics (computer science) , identification (biology) , channel (broadcasting) , artificial intelligence , feature (linguistics) , dual (grammatical number) , natural language processing , machine learning , theoretical computer science , human–computer interaction , computer network , programming language , art , linguistics , philosophy , botany , mathematics , literature , political science , pure mathematics , law , biology
Attention mechanisms are widely used in re‐identification (reID) tasks, but few attention‐based architectures have considered integrating local features with their global dependencies, that is the previous works do not model the semantic interdependencies in both spatial dimension and channel dimension. Intuitively, for person feature representations, it is important to model the interdependencies between human body semantics. In this Letter, the authors proposed a dual semantic interdependencies attention module to capture semantic interdependencies in both spatial dimension and channel dimension simultaneously. Besides, they designed a deep supervision branch to directly guide the training of the attention modules and innovatively introduce a channels random dropping mechanism in the training phase to promote the attention modules to capture more discriminative information. Extensive experimental results show that the network merging the above strategies achieves state‐of‐the‐art results on the mainstream reID data sets.