Fine-tuning CNN Image Retrieval with No Human Annotation
Open paper
Benchmark
Model
Rank
Results
image-retrieval-on-roxford-hard
R–GeM
#13
mAP: 38.5
image-retrieval-on-roxford-medium
R–GeM
#13
mAP: 64.7
image-retrieval-on-rparis-hard
R–GeM
#11
mAP: 56.3
image-retrieval-on-rparis-medium
R–GeM
#10
mAP: 77.2
Rank counts only results with a code link.