Transductive Zero-Shot Learning with Visual Structure Constraint

TL;DR

This paper introduces a transductive zero-shot learning method that uses visual structure constraints to better align semantic and visual features, effectively addressing domain shift and improving recognition of unseen classes.

Contribution

It proposes a novel visual structure constraint with three alignment strategies and a training method for real-world test scenarios, achieving state-of-the-art results.

Findings

Significant performance improvements on multiple datasets.

Effective alleviation of domain shift in ZSL.

Consistent gains across different strategies.

Abstract

To recognize objects of the unseen classes, most existing Zero-Shot Learning(ZSL) methods first learn a compatible projection function between the common semantic space and the visual space based on the data of source seen classes, then directly apply it to the target unseen classes. However, in real scenarios, the data distribution between the source and target domain might not match well, thus causing the well-known \textbf{domain shift} problem. Based on the observation that visual features of test instances can be separated into different clusters, we propose a new visual structure constraint on class centers for transductive ZSL, to improve the generality of the projection function (i.e. alleviate the above domain shift problem). Specifically, three different strategies (symmetric Chamfer-distance, Bipartite matching distance, and Wasserstein distance) are adopted to align the projected unseen semantic centers and visual cluster centers of test instances. We also propose a new training strategy to handle the real cases where many unrelated images exist in the test dataset, which is not considered in previous methods. Experiments on many widely used datasets demonstrate that the proposed visual structure constraint can bring substantial performance gain consistently and achieve state-of-the-art results. The source code is available at \url{https://github.com/raywzy/VSC}.