Zero-Shot Learning via Attribute Regression and Class Prototype Rectification

Changzhi Luo

doi:10.1109/TIP.2017.2745109

Return

Zero-Shot Learning via Attribute Regression and Class Prototype Rectification

2018-02-01

PRE

DOI：10.1109/TIP.2017.2745109

Original

Original request for help

Save

Abstract

En 中文

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.

Keywords:

Zero-shot learning

transfer knowledge

attribute regression

class prototype rectification

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.