Abstract
Semantic-descriptor-based Generalized Zero-Shot Learning (GZSL) poses challenges in recognizing the novel classes in the test phase. The development of generative models enables current GZSL techniques to probe further into the semantic-visual link, culminating in a two-stage form that includes a generator and a classifier. However, existing generation-based methods focus on enhancing the generator's effect while neglecting the improvement of the classifier. In this paper, we first conduct an analysis of two properties of the generated pseudo unseen sample: bias and homogeneity. Then, we perform variational Bayesian inference to back-derive the evaluation metrics, which reflects the balance of the seen and unseen classes. As a consequence of our derivation, the aforementioned two properties are incorporated into the classifier training as seen-unseen priors via logit adjustment. The Zero-Shot Logit Adjustment further puts semantic-based classifiers into effect in generation-based GZSL. Our experiments demonstrate that the proposed technique achieves the state of the art when combined with the basic generator, and it can improve various generative zero-shot learning frameworks. Our codes are available on \url{this https URL}.
Abstract (translated)
URL
https://arxiv.org/abs/2204.11822
