Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning

TL;DR

This paper introduces an unsupervised method for zero-shot learning that predicts class-attribute associations from class names, eliminating the need for manual annotation and enabling transfer across datasets, significantly improving performance.

Contribution

It presents a novel relation learning approach that automatically predicts class-attribute associations from class names for unsupervised zero-shot learning, with transfer capabilities across datasets.

Findings

Outperforms state-of-the-art in class-attribute association prediction

Achieves superior zero-shot classification accuracy

Enables attribute transfer across datasets

Abstract

Collecting training images for all visual categories is not only expensive but also impractical. Zero-shot learning (ZSL), especially using attributes, offers a pragmatic solution to this problem. However, at test time most attribute-based methods require a full description of attribute associations for each unseen class. Providing these associations is time consuming and often requires domain specific knowledge. In this work, we aim to carry out attribute-based zero-shot classification in an unsupervised manner. We propose an approach to learn relations that couples class embeddings with their corresponding attributes. Given only the name of an unseen class, the learned relationship model is used to automatically predict the class-attribute associations. Furthermore, our model facilitates transferring attributes across data sets without additional effort. Integrating knowledge from multiple sources results in a significant additional improvement in performance. We evaluate on two public data sets: Animals with Attributes and aPascal/aYahoo. Our approach outperforms state-of-the-art methods in both predicting class-attribute associations and unsupervised ZSL by a large margin.