A Shared Multi-Attention Framework for Multi-Label Zero-Shot Learning
Open paper
Benchmark
Model
Rank
Results
multi-label-zero-shot-learning-on-nus-wide
LESA
#7
mAP: 19.4
multi-label-zero-shot-learning-on-open-images-v4
LESA
#4
MAP: 41.7
multi-label-zero-shot-learning-on-open-images-v4
Attention per cluster
#5
MAP: 40.7
Rank counts only results with a code link.