Semi-supervised Zero-Shot Learning by a Clustering-based Approach

TL;DR

This paper introduces a semi-supervised zero-shot learning method that leverages deep visual features and clustering to recognize unseen categories, significantly improving prediction accuracy on benchmark datasets.

Contribution

It proposes a novel clustering-based semi-supervised approach that maps signatures to visual features, enhancing zero-shot learning performance.

Findings

Improves state-of-the-art accuracy on three benchmark datasets

Effectively utilizes unlabeled data for zero-shot recognition

Demonstrates robustness across multiple object recognition benchmarks

Abstract

In some of object recognition problems, labeled data may not be available for all categories. Zero-shot learning utilizes auxiliary information (also called signatures) describing each category in order to find a classifier that can recognize samples from categories with no labeled instance. In this paper, we propose a novel semi-supervised zero-shot learning method that works on an embedding space corresponding to abstract deep visual features. We seek a linear transformation on signatures to map them onto the visual features, such that the mapped signatures of the seen classes are close to labeled samples of the corresponding classes and unlabeled data are also close to the mapped signatures of one of the unseen classes. We use the idea that the rich deep visual features provide a representation space in which samples of each class are usually condensed in a cluster. The effectiveness of the proposed method is demonstrated through extensive experiments on four public benchmarks improving the state-of-the-art prediction accuracy on three of them.