Learning to Recognise Unseen Classes by A Few Similes
Yang Long, Ling Shao · 2017
Existing image classification systems often suffer from re-training models for novel unseen classes. Zero-shot learning (ZSL) aims to recognise these unseen classes directly using trained models with a further inference procedure. However, existing approaches highly rely on human-defined class-attribute associations to achieve the inference, which significantly increases the annotation cost. This paper aims to address ZSL on non-attribute tasks, i.e. only training images with labels are used as most of the supervised settings. Our main contributions are: 1) to circumvent expensive attributes, we propose to use semantic similes that directly indicate the unseen-to-seen associations; 2) a novel similarity-based representation is proposed to represent both visual images and semantic similes in a unified embedding space; 3) in order to reduce the annotation cost, we use only a few similes to infer a class-level prototype for each unseen class. On two popular benchmarks, AwA and aPY, extensive experiments manifest that our method can significantly improve the state-of-the-art results using only two similes for each unseen class. Furthermore, we revisit the Caltech 101 dataset without attributes. Our ZSL results can exceed that of previous supervised methods.