Domain segmentation and adjustment for generalized zero-shot learning

TL;DR

This paper introduces a domain segmentation and adjustment method for generalized zero-shot learning that avoids reliance on generative models, effectively addressing domain shift and class imbalance issues.

Contribution

It proposes a novel threshold and probabilistic distribution joint approach to segment and adjust test instances across seen, unseen, and uncertain domains.

Findings

Achieves competitive performance on five benchmark datasets.

Effectively mitigates domain shift without using generative models.

Provides a new perspective on handling class imbalance in zero-shot learning.

Abstract

In the generalized zero-shot learning, synthesizing unseen data with generative models has been the most popular method to address the imbalance of training data between seen and unseen classes. However, this method requires that the unseen semantic information is available during the training stage, and training generative models is not trivial. Given that the generator of these models can only be trained with seen classes, we argue that synthesizing unseen data may not be an ideal approach for addressing the domain shift caused by the imbalance of the training data. In this paper, we propose to realize the generalized zero-shot recognition in different domains. Thus, unseen (seen) classes can avoid the effect of the seen (unseen) classes. In practice, we propose a threshold and probabilistic distribution joint method to segment the testing instances into seen, unseen and uncertain domains. Moreover, the uncertain domain is further adjusted to alleviate the domain shift. Extensive experiments on five benchmark datasets show that the proposed method exhibits competitive performance compared with that based on generative models.