MKT(IN-1K)

Reported on 2 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology2 results

Zero-Shot LearningonOpen Images V4
MAP· 2022-07-05
89.2
SOTA
Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer arXiv:2207.01887
Zero-Shot LearningonNUS-WIDE
mAP· 2022-07-05
37.6
best: 42.7 (MKT(CLIP))
Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer arXiv:2207.01887