Cross-Layer Autoencoder for Zero-Shot Learning

Zilin Zhang, Yunjie Li*, Jian Yang, Yan Li, Meiguo Gao

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

11 Citations (Scopus)

Abstract

Zero-shot learning (ZSL) is the task of recognizing samples from their related classes which have never been seen during model training. ZSL is generally realized through learning a common embedding space where both high dimensional visual features and some pre-defined semantics can be mapped. However, this kind of solutions usually suffers from domain shift. In addition, the limitation and subjectivity of manual semantic information can also affect the classification results. To address these challenges, this paper proposes a novel end-to-end deep learning model called Cross-Layer Autoencoder (CLAE), which integrates different ways of semantic mapping and maintains reconstruction information. Besides, a regularized loss function is used to preserve local class manifolds. Extensive experiments for both traditional and generalized ZSL tasks are conducted on several benchmark datasets, and high effectiveness of the proposed method and its superiority over many previous researches are demonstrated.

Original languageEnglish
Article number8901216
Pages (from-to)167584-167592
Number of pages9
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - 2019

Keywords

  • Zero-shot learning
  • class manifolds
  • cross-layer autoencoder
  • regularized loss function

Fingerprint

Dive into the research topics of 'Cross-Layer Autoencoder for Zero-Shot Learning'. Together they form a unique fingerprint.

Cite this