Enhancing Semantic-Consistent Features and Transforming Discriminative Features for Generalized Zero-Shot Classifications
Generalized zero-shot learning (GZSL) aims to classify classes that do not appear during training.Recent state-of-the-art approaches rely on generative models, which use correlating semantic embeddings to synthesize unseen classes visual features; however, these approaches ignore Diabetic Otc the semantic and visual relevance, and visual features s