Multilayer Dense Connections for Hierarchical Concept Classification
This addresses the need for more comprehensive hierarchical classification in computer vision, though it is incremental as it builds on existing CNN methods.
The paper tackled the problem of CNN-based classifiers lacking hierarchical concept descriptions by proposing multilayer dense connections for concurrent prediction of categories and their superclasses, demonstrating improved performance over existing algorithms on multiple datasets.
Classification is a pivotal function for many computer vision tasks such as object classification, detection, scene segmentation. Multinomial logistic regression with a single final layer of dense connections has become the ubiquitous technique for CNN-based classification. While these classifiers project a mapping between the input and a set of output category classes, they do not typically yield a comprehensive description of the category. In particular, when a CNN based image classifier correctly identifies the image of a Chimpanzee, its output does not clarify that Chimpanzee is a member of Primate, Mammal, Chordate families and a living thing. We propose a multilayer dense connectivity for concurrent prediction of category and its conceptual superclasses in hierarchical order by the same CNN. We experimentally demonstrate that our proposed network can simultaneously predict both the coarse superclasses and finer categories better than several existing algorithms in multiple datasets.