Office-Home

홈페이지 · 논문 1,074편

Office-Home is a benchmark dataset for domain adaptation which contains 4 domains where each domain consists of 65 categories. The four domains are: Art – artistic images in the form of sketches, paintings, ornamentation, etc.; Clipart – collection of clipart images; Product – images of objects without a background and Real-World – images of objects captured with a regular camera. It contains 15,500 images, with an average of around 70 images per class and a maximum of 99 images in a class. Source: Multi-component Image Translation for Deep Domain Generalization Image Source: Wen et al

Images

벤치마크

Domain Generalization on Office-Home 결과 90개

Unsupervised Domain Adaptation on Office-Home 결과 40개

Domain Adaptation on Office-Home 결과 29개

Universal Domain Adaptation on Office-Home 결과 28개

Partial Domain Adaptation on Office-Home 결과 11개

Unsupervised Domain Adaptation on Office-Home (RS-UT imbalance) 결과 10개

Transfer Learning on Office-Home 결과 5개

Multi-target Domain Adaptation on Office-Home 결과 4개

cross-domain few-shot learning on Office-Home 결과 3개

Blended-target Domain Adaptation on Office-Home 결과 2개

Open-Set Multi-Target Domain Adaptation on Office-Home 결과 1개