div> Abstract Humans can naturally understand an image in depth with the aid of rich knowledge accumulated from daily lives or professions. For example, to achieve fifine-grained image recognition (e.g., categorizing hundreds of subordinate categories of birds) usually requires a comprehensive visual concept organization including category labels and part-level attributes. In this work, we investigate how to unify rich professional knowledge with deep neural network architectures and propose a Knowledge-Embedded Representation Learning (KERL) framework for handling the problem of fifine-grained image recognition. Specififically, we organize the rich visual concepts in the form of knowledge graph and employ a Gated Graph Neural Network to propagate node message through the graph for generating the knowledge representation. By introducing a novel gated mechanism, our KERL framework incorporates this knowledge representation into the discriminative image feature learning, i.e., implicitly associating the specifific attributes with the feature maps. Compared with existing methods of fifine-grained image classifification, our KERL framework has several appealing properties: i) The embedded high-level knowledge enhances the feature representation, thus facilitating distinguishing the subtle differences among subordinate categories. ii) Our framework can learn feature maps with a meaningful confifiguration that the highlighted regions fifinely accord with the nodes (specifific attributes) of the knowledge graph. Extensive experiments on the widely used CaltechUCSD bird dataset demonstrate the superiority of ∗Corresponding author is Liang Lin (Email: linliang@ieee.org). This work was supported by the National Natural Science Foundation of China under Grant 61622214, the Science and Technology Planning Project of Guangdong Province under Grant 2017B010116001, and Guangdong Natural Science Foundation Project for Research Teams under Grant 2017A030312006.