paper-with-me

MIT-States

홈페이지 · 논문 91편

The MIT-States dataset has 245 object classes, 115 attribute classes and ∼53K images. There is a wide range of objects (e.g., fish, persimmon, room) and attributes (e.g., mossy, deflated, dirty). On average, each object instance is modified by one of the 9 attributes it affords. Source: Attributes as Operators: Factorizing Unseen Attribute-Object Compositions Image Source: http://web.mit.edu/phillipi/Public/states_and_transformations/index.html

Images

벤치마크

Image Retrieval with Multi-Modal Query on MIT-States 결과 5개

Compositional Zero-Shot Learning on MIT-States 결과 2개

Compositional Zero-Shot Learning on MIT-States, generalized split 결과 2개

Zero-Shot Learning on MIT-States 결과 1개