Transductive Unbiased Embedding for Zero-Shot Learning

TL;DR

This paper introduces QFSL, a transductive learning approach that reduces bias in zero-shot learning by utilizing both labeled source and unlabeled target data, significantly improving performance.

Contribution

The paper proposes a novel transductive method, QFSL, that effectively alleviates bias in ZSL by mapping source and target images to fixed points in semantic space.

Findings

Outperforms state-of-the-art methods by 9.3-24.5% in generalized ZSL

Achieves 0.2-16.2% improvement in conventional ZSL

Demonstrates effectiveness on AwA2, CUB, and SUN datasets

Abstract

Most existing Zero-Shot Learning (ZSL) methods have the strong bias problem, in which instances of unseen (target) classes tend to be categorized as one of the seen (source) classes. So they yield poor performance after being deployed in the generalized ZSL settings. In this paper, we propose a straightforward yet effective method named Quasi-Fully Supervised Learning (QFSL) to alleviate the bias problem. Our method follows the way of transductive learning, which assumes that both the labeled source images and unlabeled target images are available for training. In the semantic embedding space, the labeled source images are mapped to several fixed points specified by the source categories, and the unlabeled target images are forced to be mapped to other points specified by the target categories. Experiments conducted on AwA2, CUB and SUN datasets demonstrate that our method outperforms existing state-of-the-art approaches by a huge margin of 9.3~24.5% following generalized ZSL settings, and by a large margin of 0.2~16.2% following conventional ZSL settings.