Class-Prototype Discriminative Network for Generalized Zero-Shot Learning

• Published in: IEEE signal processing letters Vol. 27; pp. 301 - 305
• Main Authors: Huang, Sheng, Lin, Jingkai, Huangfu, Luwen
• Format: Journal Article
• Language: English
• Published: New York IEEE 2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Analogies; cross-modal metric learning; deep learning; Feature extraction; Measurement; Prototypes; relation network; Semantics; Task analysis; Training; Visualization; Zero-shot learning
• ISSN: 1070-9908; 1558-2361
• DOI: 10.1109/LSP.2020.2968213

We present a novel end-to-end deep metric learning model named Class-Prototype Discriminative Network (CPDN) for Generalized Zero-Shot Learning (GZSL). It consists of a generative network for producing the visual prototype of each class by feeding its semantic representation, and a metric network for measuring the similarities between the sample and the generated class-prototypes to accomplish the classification. In CPDN, a query sample intends to posses a higher similarity with its homogenous class-prototypes while the lower similarities with the inhomogenous ones, and the class-prototypes also intend to be distinguished with each other through the metric network. Moreover, a discriminative version of Relation Network (RN) named Discriminative Relation Network (DRN) is presented by incorporating the aforementioned idea into the conventional RN model for further achieving the complementation CDPN and RN in metric learning. Extensive experimental results on standard benchmarks demonstrate that our proposed approaches consistently outperform RN, and achieve the competitive performances compared with the state-of-the-arts in GZSL.