Probabilistic Zero-shot Classification with Semantic Rankings
This work addresses zero-shot classification problems by enabling more accurate predictions through aggregated semantic information, though it appears incremental as it builds on existing pre-trained classifiers without retraining.
The paper tackles zero-shot learning by proposing a ranking-based representation for semantic similarity that aggregates multiple heterogeneous sources, and demonstrates improved classification accuracy on two large real-world image datasets.
In this paper we propose a non-metric ranking-based representation of semantic similarity that allows natural aggregation of semantic information from multiple heterogeneous sources. We apply the ranking-based representation to zero-shot learning problems, and present deterministic and probabilistic zero-shot classifiers which can be built from pre-trained classifiers without retraining. We demonstrate their the advantages on two large real-world image datasets. In particular, we show that aggregating different sources of semantic information, including crowd-sourcing, leads to more accurate classification.