Generalized zero-shot learning (GZSL) is focused on recognizing classes, both seen and unseen, without the need for labeled data specifically for the unseen classes. GZSL has attracted much attention by transforming the traditional GZSL into a fully supervised learning task. Most GZSL methods use a single semantic attribute (each category can only correspond to a specific semantic attribute) plus Gaussian noise to generate visual features, assuming a one-to-one correspondence between these visual features and single semantic attributes. However, in practice, there may be cases of attribute missingness in images, leading to visual features that lack certain attributes, thus failing to achieve a good mapping between semantic attributes and visual features. Therefore, visual features of the same class should have diverse semantic attributes. To address this issue, we propose a new method for enhancing semantic attributes called “Interpolated Semantic Attribute Enhancement for Generalized Zero-Shot Learning (ISAE-GZSL).” This method uses interpolation to deal with the problem of semantic attribute missingness in real-world situations, thereby enhancing semantic diversity and generating more realistic and diverse visual features. We assess the performance of the proposed model across four benchmark datasets, and the findings demonstrate substantial enhancements over current state-of-the-art methods, especially in handling categories with severe attribute missingness in the datasets.