Zero-Shot Learning via Attribute Regression and Class Prototype Rectification

Changzhi Luo, Zhetao Li*, Kaizhu Huang, Jiashi Feng, Meng Wang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

54 Citations (Scopus)


Zero-Shot learning (ZSL) aims at classifying examples for unseen classes (with no training examples) given some other seen classes (with training examples). Most existing approaches exploit intermedia-level information (e.g., attributes) to transfer knowledge from seen classes to unseen classes. A common practice is to first learn projections from samples to attributes on seen classes via a regression method, and then apply such projections to unseen classes directly. However, it turns out that such a manner of learning strategy easily causes projection domain shift problem and hubness problem, which hinder the performance of ZSL task. In this paper, we also formulate ZSL as an attribute regression problem. However, different from general regression-based solutions, the proposed approach is novel in three aspects. First, a class prototype rectification method is proposed to connect the unseen classes to the seen classes. Here, a class prototype refers to a vector representation of a class, and it is also known as a class center, class signature, or class exemplar. Second, an alternating learning scheme is proposed for jointly performing attribute regression and rectifying the class prototypes. Finally, a new objective function which takes into consideration both the attribute regression accuracy and the class prototype discrimination is proposed. By introducing such a solution, domain shift problem and hubness problem can be mitigated. Experimental results on three public datasets (i.e., CUB200-2011, SUN Attribute, and aPaY) well demonstrate the effectiveness of our approach.

Original languageEnglish
Article number8016672
Pages (from-to)637-648
Number of pages12
JournalIEEE Transactions on Image Processing
Issue number2
Publication statusPublished - Feb 2018


  • Attribute regression
  • Class prototype rectification
  • Transfer knowledge
  • Zero-Shot learning


Dive into the research topics of 'Zero-Shot Learning via Attribute Regression and Class Prototype Rectification'. Together they form a unique fingerprint.

Cite this