Improving Generalized Zero-Shot Learning by Semantic Discriminator
This addresses a specific bottleneck in GZSL for researchers, but it is incremental as it builds on prior ZSL techniques.
The paper tackles the problem of low classification accuracy for unseen classes in Generalized Zero-Shot Learning (GZSL) by proposing a Semantic Discriminator (SD) to distinguish between seen and unseen domains, resulting in improved performance when combined with existing methods.
It is a recognized fact that the classification accuracy of unseen classes in the setting of Generalized Zero-Shot Learning (GZSL) is much lower than that of traditional Zero-Shot Leaning (ZSL). One of the reasons is that an instance is always misclassified to the wrong domain. Here we refer to the seen and unseen classes as two domains respectively. We propose a new approach to distinguish whether the instances come from the seen or unseen classes. First the visual feature of instance is projected into the semantic space. Then the absolute norm difference between the projected semantic vector and the class semantic embedding vector, and the minimum distance between the projected semantic vectors and the semantic embedding vectors of the seen classes are used as discrimination basis. This approach is termed as SD (Semantic Discriminator) because domain judgement of instance is performed in the semantic space. Our approach can be combined with any existing ZSL method and fully supervision classification model to form a new GZSL method. Furthermore, our approach is very simple and does not need any fixed parameters.