论文标题
将句子用作大规模零声学习的语义表示
Using Sentences as Semantic Representations in Large Scale Zero-Shot Learning
论文作者
论文摘要
零拍的学习旨在识别未见类的实例，在培训期间没有可用的视觉实例，通过学习可见类和相应类语义表示的样本之间的多模式关系。这些类的表示通常由属性组成，这些属性不能很好地扩展到大型数据集，也不是单词嵌入的属性，这会导致性能较差。一个良好的权衡可能是用自然语言作为班级描述使用简短的句子。我们探索在ZSL设置中使用此类简短描述的不同解决方案，并表明，尽管简单的方法无法单独使用句子获得很好的结果，但是通常的单词嵌入和句子的组合可以显着胜过当前的最新目前。
Zero-shot learning aims to recognize instances of unseen classes, for which no visual instance is available during training, by learning multimodal relations between samples from seen classes and corresponding class semantic representations. These class representations usually consist of either attributes, which do not scale well to large datasets, or word embeddings, which lead to poorer performance. A good trade-off could be to employ short sentences in natural language as class descriptions. We explore different solutions to use such short descriptions in a ZSL setting and show that while simple methods cannot achieve very good results with sentences alone, a combination of usual word embeddings and sentences can significantly outperform current state-of-the-art.
