Boosting Generative Zero-Shot Learning by Synthesizing Diverse Features with Attribute Augmentation
This work addresses the challenge of generating realistic visual features for zero-shot learning, which is important for AI systems that need to recognize objects without prior examples, though it is incremental as it builds on existing generative approaches.
The paper tackled the problem of generative zero-shot learning by addressing the limitation of using a single semantic attribute for feature generation, which leads to incomplete semantics. The proposed method uses augmented semantic attributes to synthesize diverse features, achieving significant performance improvements on four benchmark datasets.
The recent advance in deep generative models outlines a promising perspective in the realm of Zero-Shot Learning (ZSL). Most generative ZSL methods use category semantic attributes plus a Gaussian noise to generate visual features. After generating unseen samples, this family of approaches effectively transforms the ZSL problem into a supervised classification scheme. However, the existing models use a single semantic attribute, which contains the complete attribute information of the category. The generated data also carry the complete attribute information, but in reality, visual samples usually have limited attributes. Therefore, the generated data from attribute could have incomplete semantics. Based on this fact, we propose a novel framework to boost ZSL by synthesizing diverse features. This method uses augmented semantic attributes to train the generative model, so as to simulate the real distribution of visual features. We evaluate the proposed model on four benchmark datasets, observing significant performance improvement against the state-of-the-art.