Towards Light-weight Annotations: Fuzzy Interpolative Reasoning for Zero-shot Image Classification

Yang Long, Yao Tan, Daniel Organisciak, Longzhi Yang, Ling Shao

Research output: Contribution to conferencePaperpeer-review

1 Citation (Scopus)
42 Downloads (Pure)


Despite the recent popularity of Zero-shot Learning (ZSL) techniques, existing approaches rely on ontological engineering with heavy annotations to supervise the transferable attribute model that can go across seen and unseen classes. Moreover, existing cross-sourcing, expert-based, or data-driven attribute annotations (e.g. Word Embeddings) cannot guarantee sufficient description to the visual features, which leads to significant performance degradation. In order to circumvent the expensive attribute annotations while retaining the reliability, we propose a Fuzzy Interpolative Reasoning (FIR) algorithm that can discover inter-class associations from light-weight Simile annotations based on visual similarities between classes. The inferred representation can better bridge the visual-semantic gap and manifest state-of-the-art experimental results.
Original languageEnglish
Number of pages12
Publication statusPublished - 3 Sept 2018
EventBMVC 2018 - British Machine Vision Conference -
Duration: 3 Sept 20186 Sept 2018


ConferenceBMVC 2018 - British Machine Vision Conference
Internet address


Dive into the research topics of 'Towards Light-weight Annotations: Fuzzy Interpolative Reasoning for Zero-shot Image Classification'. Together they form a unique fingerprint.

Cite this